page-006

Challenge: Ordinary diary prose beginning and ending mid-entry; the supplied manifest reports 17 OCR words while literal TSV parsing finds 407.

Agent-reviewed material is diagnostic only. The page image is authoritative.

Authoritative page image

Scanned source page-006

Owner status: owner_approved

Explicit owner approval is recorded. The historical model candidate and agent diagnostic remain available below.

Uncertainties

None recorded

Editorial and review notes

Current edition reading text

Thanks to our Heavenly Father.  The day was spent pleasantly, by reading and conversation, and after "tea" just before the song service I went in with Miss Slater and had a nice talk with her sister who is very ill - we had prayer and came out to the song service. After which a little walk on deck, and down in the saloon again while I am writing, Miss Holland is punching my hand with a long pole.  I am at a table with a lot of English men and women.  Now the steward says it is eleven o'clock & shuts off the lights so I retire to my state room and Mr. Morrison & myself eat an apple each.

Nov. 16 - Monday
Rather late about arising  great preparations about getting ready to land.  Drawing in toward Ireland. Nothing of importance happened except I became much interested in Miss Jennie Holland, and we had several nice walks together.  I told her how I liked her and How I hated to leave her - we were out until after 12 midnight and then I Packed my trunk and telescope preparatory to landing at Queenstown at 3 o'clock Tuesday morning.

Nov. 17 - Tuesday
At 4 o'clock this a.m. the steward called me to get up and have some coffee as we were soon to stop at Queenstown.  I got up and nearly all on board got up to see those off who were going to land at Q.  But something was wrong at the signal stations and the tender (the boat on which we were unloaded) did not get the news of our arrival so we anchored about 2 hours.  Miss H and myself had a nice-pleasant time walking and talking until the tender came.  I then got on the tender and went up the Cork Harbor to Queenstown about an hour's ride.  The water in the harbor was very placid and as it was just getting light the hills & garrisons on either side looked beautiful.  The scenery is grand.  We arrived at Q. at 7 a.m. I together with a lot of others, and went into the Custom House and had our packages opened and inspected - no goods which were subject to duty, except a box of cigars which I was careful to take out of the box and put in my overcoat pocket.  I then went uptown with Mrs. Abraham, the Garrigan

Current edition diplomatic rendering

Thanks to our Heavenly Father.  The day was spent
pleasantly, by reading and conversation, and after
"tea" just before the song service I went in with Miss
Slater and had a nice talk with her sister who is very
ill - we had prayer and came out to the song service.
After which a little walk on deck, and down in the
saloon again while I am writing, Miss Holland is punch-
ing my hand with a long pole.  I am at a table with a
lot of English men and women.  Now the steward says it
is eleven o'clock & shuts off the lights so I retire to
my state room and Mr. Morrison & myself eat an apple
each.

Nov. 16 - Monday
Rather late about arising  great preparations about
getting ready to land.  Drawing in toward Ireland.
Nothing of importance happened except I became much
interested in Miss Jennie Holland, and we had several
nice walks together.  I told her how I liked her and
How I hated to leave her - we were out until after 12
midnight and then I Packed my trunk and telescope
preparatory to landing at Queenstown at 3 o'clock
Tuesday morning.

Nov. 17 - Tuesday
At 4 o'clock this a.m. the steward called me to get
up and have some coffee as we were soon to stop at
Queenstown.  I got up and nearly all on board got up
to see those off who were going to land at Q.  But
something was wrong at the signal stations and the
tender (the boat on which we were unloaded) did not
get the news of our arrival so we anchored about 2
hours.  Miss H and myself had a nice-pleasant time
walking and talking until the tender came.  I then
got on the tender and went up the Cork Harbor to
Queenstown about an hour's ride.  The water in the
harbor was very placid and as it was just getting
light the hills & garrisons on either side looked
beautiful.  The scenery is grand.  We arrived at Q.
at 7 a.m. I together with a lot of others, and went
into the Custom House and had our packages opened
and inspected - no goods which were subject to duty,
except a box of cigars which I was careful to take
out of the box and put in my overcoat pocket.  I
then went uptown with Mrs. Abraham, the Garrigan

Raw OCR

open text file

Thanks to our Heavenly Father. The day was spent
pleasantly, by reading and conversation, and after
"teal just before the song service I went in with Miss
Slater and had a nice talk with her sister who is very
ill ~ we had prayer and came out to the song service.
After which a little walk on deck, and down in the
saloon again while I am writing, Miss Holland is punch-
ing my hand with a long pole. I am at a table with a
lot of English men and women. Now the steward says it
isa eleven o'clock & shuts off the lights so I retire to

my state room and Mr. Morrison & myself eat an apple
each.

Nov. 16 ~ Monday

Rather late about arising great preparations about
getting ready to land. Drawing in toward Ireland.
Nothing of importance happened except I became much
interested in Miss Jennie Holland, and we had several
nice walks together. I told her how I liked her and
How I hated to leave her - we were out until after 12
midnight and then I Packed my trunk and telescope
preparatory to landing at Queenstown at 3 o'clock
Tuesday morning.

Nov. 17 - Tuesday

At 4 o'clock this awn. the steward called me to get
up and have some coffee as we were soon to stop at
Queenstown. I got up and nearly all on board got up
to see those off who were going to land at Q. But
something was wrong at the signal stations and the
tender (the boat on which we were unloaded) did not
get the news of our arrival so we anchored about 2
hours. Miss H and myself had a nice-pleasant time
walking and talking until the tender came. I then
got on the tender and went up the Cork Harbor to
Queenstown about an hour's ride. The water in the
harbor was very placid and as it was just getting
light the hills & garrisons on either side looked
beautiful. The scenery is grand. We arrived at Q.
at 7 aem. I together with a lot of others, and went
into the Custom House and had our packages opened
and inspected - no goods which were subject to duty,
except a box of cigars which I was careful to take
out of the box and put in my overcoat pocket. I
then went uptown with Mrs. Abraham, the Garrigan

Candidate-to-diagnostic reading diff

--- candidate-reading

+++ diagnostic-reading

@@ -4,4 +4,4 @@

 Rather late about arising  great preparations about getting ready to land.  Drawing in toward Ireland. Nothing of importance happened except I became much interested in Miss Jennie Holland, and we had several nice walks together.  I told her how I liked her and How I hated to leave her - we were out until after 12 midnight and then I Packed my trunk and telescope preparatory to landing at Queenstown at 3 o'clock Tuesday morning.
 
 Nov. 17 - Tuesday
-At 4 o'clock this a.m. the steward called me to get up and have some coffee as we were soon to stop at Queenstown.  I got up and nearly all on board got up to see those off who were going to land at Q.  But something was wrong at the signal stations and the tender (the boat on which we were unloaded) did not get the news of our arrival so we anchored about 2 hours.  Miss H and myself had a nice pleasant time walking and talking until the tender came.  I then got on the tender and went up the Cork Harbor to Queenstown about an hour's ride.  The water in the harbor was very placid and as it was just getting light the hills & garrisons on either side looked beautiful.  The scenery is grand.  We arrived at Q. at 7 a.m. I together with a lot of others, and went into the Custom House and had our packages opened and inspected - no goods which were subject to duty, except a box of cigars which I was careful to take out of the box and put in my overcoat pocket.  I then went uptown with Mrs. Abraham, the Garrigan
+At 4 o'clock this a.m. the steward called me to get up and have some coffee as we were soon to stop at Queenstown.  I got up and nearly all on board got up to see those off who were going to land at Q.  But something was wrong at the signal stations and the tender (the boat on which we were unloaded) did not get the news of our arrival so we anchored about 2 hours.  Miss H and myself had a nice-pleasant time walking and talking until the tender came.  I then got on the tender and went up the Cork Harbor to Queenstown about an hour's ride.  The water in the harbor was very placid and as it was just getting light the hills & garrisons on either side looked beautiful.  The scenery is grand.  We arrived at Q. at 7 a.m. I together with a lot of others, and went into the Custom House and had our packages opened and inspected - no goods which were subject to duty, except a box of cigars which I was careful to take out of the box and put in my overcoat pocket.  I then went uptown with Mrs. Abraham, the Garrigan

Candidate-to-diagnostic canonical JSON diff

Categories: textual_transcription

--- model-candidate

+++ agent-diagnostic

@@ -1,5 +1,5 @@

 {
-  "schema_version": "1.0.0",
+  "schema_version": "1.1.0",
   "page_id": "page-006",
   "source": {
     "pdf_page": 6,
@@ -904,7 +904,7 @@

               "segments": [
                 {
                   "type": "text",
-                  "text": "hours.  Miss H and myself had a nice pleasant time"
+                  "text": "hours.  Miss H and myself had a nice-pleasant time"
                 }
               ],
               "line_end": "no_hyphen"
@@ -1060,16 +1060,24 @@

         "actor": "codex-exec:gpt-5.6-sol",
         "artifact": "20260808T180301Z-eval",
         "created_at": "2026-08-08T18:03:49Z"
+      },
+      {
+        "kind": "agent_review",
+        "actor": "Codex",
+        "artifact": "artifacts/runs/20260808T180301Z-eval/candidates/page-006.json",
+        "created_at": "2026-08-08T18:09:26Z"
       }
     ]
   },
   "review": {
-    "status": "model_candidate",
+    "status": "agent_reviewed",
     "authority": "diagnostic_only",
-    "reviewer": null,
-    "reviewed_at": null,
+    "reviewer": "Codex",
+    "reviewed_at": "2026-08-08T18:09:26Z",
     "notes": [
-      "Model candidate only; the page image remains authoritative."
+      "Diagnostic fixture only; it is not independent ground truth and has not been owner-approved.",
+      "Compared the complete page transcription with the authoritative page image.",
+      "Corrected the visibly intentional source hyphen in nice-pleasant; the model had silently omitted it."
     ]
   }
 }

Diagnostic-to-owner reading diff

No reading-text difference.

Diagnostic-to-owner canonical JSON diff

--- agent-diagnostic

+++ owner-approved-edition

@@ -1066,18 +1066,30 @@

         "actor": "Codex",
         "artifact": "artifacts/runs/20260808T180301Z-eval/candidates/page-006.json",
         "created_at": "2026-08-08T18:09:26Z"
+      },
+      {
+        "kind": "owner_review",
+        "actor": "John Crowley",
+        "artifact": "evaluation/goldens/page-006.json",
+        "created_at": "2026-08-08T20:02:47Z",
+        "action": "approve_as_is",
+        "input_sha256": "77fc639f18af7b5f576a7ef0eb3fd30008107b36a3c5fa0bbe66df168ed44b02",
+        "change_categories": []
       }
     ]
   },
   "review": {
-    "status": "agent_reviewed",
-    "authority": "diagnostic_only",
-    "reviewer": "Codex",
-    "reviewed_at": "2026-08-08T18:09:26Z",
+    "status": "owner_approved",
+    "authority": "owner_approved_edition",
+    "reviewer": "John Crowley",
+    "reviewed_at": "2026-08-08T20:02:47Z",
     "notes": [
       "Diagnostic fixture only; it is not independent ground truth and has not been owner-approved.",
       "Compared the complete page transcription with the authoritative page image.",
-      "Corrected the visibly intentional source hyphen in nice-pleasant; the model had silently omitted it."
+      "Corrected the visibly intentional source hyphen in nice-pleasant; the model had silently omitted it.",
+      "Explicit owner action: approve_as_is.",
+      "Approval lineage begins with diagnostic SHA-256 77fc639f18af7b5f576a7ef0eb3fd30008107b36a3c5fa0bbe66df168ed44b02.",
+      "Owner visually compared the diagnostic with the authoritative scan and approved it without further changes."
     ]
   }
 }
Raw model candidate JSON

open JSON

{
  "schema_version": "1.0.0",
  "page_id": "page-006",
  "source": {
    "pdf_page": 6,
    "source_pdf_sha256": "80a074ed94fded84fa8a455d61fbf94b25cd4f1239d5ec3e639aaf443467c53f",
    "image": {
      "path": "pages/page-006.png",
      "sha256": "54324af70b4ce807f7bdde2a88446d7bbd3fa46aacf95d87c55db521cba05e10",
      "width": 1700,
      "height": 2200,
      "dpi": 200
    },
    "ocr": {
      "text_path": "ocr/page-006.txt",
      "text_sha256": "c43acc671cbe2c1f386b948a4c229bd03821071d0ea9ff94b1a545d8451acda0",
      "tsv_path": "ocr/page-006.tsv",
      "tsv_sha256": "869b2b51411feb1ebf78b23a45b0ceb5a29389f55d1f32f9dffeec18ba8f7e2e",
      "engine": "tesseract 5.5.0"
    }
  },
  "segment": {
    "id": "book-01",
    "kind": "book",
    "label_source": "First book",
    "assignment_status": "inferred"
  },
  "page_role": "content",
  "boundary": {
    "starts_mid_block": "yes",
    "ends_mid_block": "yes"
  },
  "blocks": [
    {
      "id": "p006-b001",
      "order": 1,
      "continuation": {
        "from_previous": "yes",
        "to_next": "no",
        "previous": null,
        "next": null
      },
      "evidence": {
        "status": "partial",
        "method": "exact_normalized_token_sequence",
        "ocr_word_ids": [
          "p006-b001-r001-l001-w001",
          "p006-b001-r001-l001-w002",
          "p006-b001-r001-l001-w003",
          "p006-b001-r001-l001-w004",
          "p006-b001-r001-l001-w005",
          "p006-b001-r001-l001-w006",
          "p006-b001-r001-l001-w007",
          "p006-b001-r001-l001-w008",
          "p006-b001-r001-l001-w009",
          "p006-b001-r001-l002-w001",
          "p006-b001-r001-l002-w002",
          "p006-b001-r001-l002-w003",
          "p006-b001-r001-l002-w004",
          "p006-b001-r001-l002-w005",
          "p006-b001-r001-l002-w006",
          "p006-b001-r001-l002-w007",
          "p006-b001-r001-l003-w002",
          "p006-b001-r001-l003-w003",
          "p006-b001-r001-l003-w004",
          "p006-b001-r001-l003-w005",
          "p006-b001-r001-l003-w006",
          "p006-b001-r001-l003-w007",
          "p006-b001-r001-l003-w008",
          "p006-b001-r001-l003-w009",
          "p006-b001-r001-l003-w010",
          "p006-b001-r001-l003-w011",
          "p006-b001-r001-l004-w001",
          "p006-b001-r001-l004-w002",
          "p006-b001-r001-l004-w003",
          "p006-b001-r001-l004-w004",
          "p006-b001-r001-l004-w005",
          "p006-b001-r001-l004-w006",
          "p006-b001-r001-l004-w007",
          "p006-b001-r001-l004-w008",
          "p006-b001-r001-l004-w009",
          "p006-b001-r001-l004-w010",
          "p006-b001-r001-l004-w011",
          "p006-b001-r001-l004-w012",
          "p006-b001-r001-l005-w001",
          "p006-b001-r001-l005-w003",
          "p006-b001-r001-l005-w004",
          "p006-b001-r001-l005-w005",
          "p006-b001-r001-l005-w006",
          "p006-b001-r001-l005-w007",
          "p006-b001-r001-l005-w008",
          "p006-b001-r001-l005-w009",
          "p006-b001-r001-l005-w010",
          "p006-b001-r001-l005-w011",
          "p006-b001-r001-l005-w012",
          "p006-b001-r001-l006-w001",
          "p006-b001-r001-l006-w002",
          "p006-b001-r001-l006-w003",
          "p006-b001-r001-l006-w004",
          "p006-b001-r001-l006-w005",
          "p006-b001-r001-l006-w006",
          "p006-b001-r001-l006-w007",
          "p006-b001-r001-l006-w008",
          "p006-b001-r001-l006-w009",
          "p006-b001-r001-l006-w010",
          "p006-b001-r001-l006-w011",
          "p006-b001-r001-l007-w001",
          "p006-b001-r001-l007-w002",
          "p006-b001-r001-l007-w003",
          "p006-b001-r001-l007-w004",
          "p006-b001-r001-l007-w005",
          "p006-b001-r001-l007-w006",
          "p006-b001-r001-l007-w007",
          "p006-b001-r001-l007-w008",
          "p006-b001-r001-l007-w009",
          "p006-b001-r001-l008-w002",
          "p006-b001-r001-l008-w003",
          "p006-b001-r001-l008-w004",
          "p006-b001-r001-l008-w005",
          "p006-b001-r001-l008-w006",
          "p006-b001-r001-l008-w007",
          "p006-b001-r001-l008-w008",
          "p006-b001-r001-l008-w009",
          "p006-b001-r001-l008-w010",
          "p006-b001-r001-l008-w011",
          "p006-b001-r001-l008-w012",
          "p006-b001-r001-l008-w013",
          "p006-b001-r001-l008-w014",
          "p006-b001-r001-l009-w001",
          "p006-b001-r001-l009-w002",
          "p006-b001-r001-l009-w003",
          "p006-b001-r001-l009-w004",
          "p006-b001-r001-l009-w005",
          "p006-b001-r001-l009-w006",
          "p006-b001-r001-l009-w007",
          "p006-b001-r001-l009-w008",
          "p006-b001-r001-l009-w009",
          "p006-b001-r001-l009-w010",
          "p006-b001-r001-l009-w011",
          "p006-b001-r001-l010-w002",
          "p006-b001-r001-l010-w003",
          "p006-b001-r001-l010-w005",
          "p006-b001-r001-l010-w006",
          "p006-b001-r001-l010-w007",
          "p006-b001-r001-l010-w008",
          "p006-b001-r001-l010-w009",
          "p006-b001-r001-l010-w010",
          "p006-b001-r001-l010-w011",
          "p006-b001-r001-l010-w012",
          "p006-b002-r001-l001-w001",
          "p006-b002-r001-l001-w002",
          "p006-b002-r001-l001-w003",
          "p006-b002-r001-l001-w004",
          "p006-b002-r001-l001-w005",
          "p006-b002-r001-l001-w006",
          "p006-b002-r001-l001-w008",
          "p006-b002-r001-l001-w009",
          "p006-b002-r001-l001-w010",
          "p006-b002-r001-l001-w011",
          "p006-b002-r001-l002-w001"
        ],
        "bbox": {
          "x": 350,
          "y": 406,
          "width": 925,
          "height": 391
        },
        "matched_tokens": 114,
        "total_tokens": 117
      },
      "type": "diary_entry",
      "date": null,
      "place_source": null,
      "content": [
        {
          "id": "p006-b001-p001",
          "order": 1,
          "evidence": {
            "status": "not_attempted",
            "method": null,
            "ocr_word_ids": [],
            "bbox": null,
            "matched_tokens": 0,
            "total_tokens": 0
          },
          "type": "text",
          "role": "body",
          "lines": [
            {
              "line_number": 1,
              "segments": [
                {
                  "type": "text",
                  "text": "Thanks to our Heavenly Father.  The day was spent"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 2,
              "segments": [
                {
                  "type": "text",
                  "text": "pleasantly, by reading and conversation, and after"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 3,
              "segments": [
                {
                  "type": "text",
                  "text": "\"tea\" just before the song service I went in with Miss"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 4,
              "segments": [
                {
                  "type": "text",
                  "text": "Slater and had a nice talk with her sister who is very"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 5,
              "segments": [
                {
                  "type": "text",
                  "text": "ill - we had prayer and came out to the song service."
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 6,
              "segments": [
                {
                  "type": "text",
                  "text": "After which a little walk on deck, and down in the"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 7,
              "segments": [
                {
                  "type": "text",
                  "text": "saloon again while I am writing, Miss Holland is punch"
                }
              ],
              "line_end": "hyphen_word_break"
            },
            {
              "line_number": 8,
              "segments": [
                {
                  "type": "text",
                  "text": "ing my hand with a long pole.  I am at a table with a"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 9,
              "segments": [
                {
                  "type": "text",
                  "text": "lot of English men and women.  Now the steward says it"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 10,
              "segments": [
                {
                  "type": "text",
                  "text": "is eleven o'clock & shuts off the lights so I retire to"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 11,
              "segments": [
                {
                  "type": "text",
                  "text": "my state room and Mr. Morrison & myself eat an apple"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 12,
              "segments": [
                {
                  "type": "text",
                  "text": "each."
                }
              ],
              "line_end": "block_end"
            }
          ]
        }
      ]
    },
    {
      "id": "p006-b002",
      "order": 2,
      "continuation": {
        "from_previous": "no",
        "to_next": "no",
        "previous": null,
        "next": null
      },
      "evidence": {
        "status": "aligned",
        "method": "exact_normalized_token_sequence",
        "ocr_word_ids": [
          "p006-b003-r001-l001-w001",
          "p006-b003-r001-l001-w002",
          "p006-b003-r001-l001-w004",
          "p006-b003-r002-l001-w001",
          "p006-b003-r002-l001-w002",
          "p006-b003-r002-l001-w003",
          "p006-b003-r002-l001-w004",
          "p006-b003-r002-l001-w005",
          "p006-b003-r002-l001-w006",
          "p006-b003-r002-l001-w007",
          "p006-b003-r002-l002-w001",
          "p006-b003-r002-l002-w002",
          "p006-b003-r002-l002-w003",
          "p006-b003-r002-l002-w004",
          "p006-b003-r002-l002-w005",
          "p006-b003-r002-l002-w006",
          "p006-b003-r002-l002-w007",
          "p006-b003-r002-l002-w008",
          "p006-b003-r002-l003-w001",
          "p006-b003-r002-l003-w002",
          "p006-b003-r002-l003-w003",
          "p006-b003-r002-l003-w004",
          "p006-b003-r002-l003-w005",
          "p006-b003-r002-l003-w006",
          "p006-b003-r002-l003-w007",
          "p006-b003-r002-l003-w008",
          "p006-b003-r002-l004-w001",
          "p006-b003-r002-l004-w002",
          "p006-b003-r002-l004-w003",
          "p006-b003-r002-l004-w004",
          "p006-b003-r002-l004-w005",
          "p006-b003-r002-l004-w006",
          "p006-b003-r002-l004-w007",
          "p006-b003-r002-l004-w008",
          "p006-b003-r002-l004-w009",
          "p006-b003-r002-l005-w001",
          "p006-b003-r002-l005-w002",
          "p006-b003-r002-l005-w003",
          "p006-b003-r002-l005-w004",
          "p006-b003-r002-l005-w005",
          "p006-b003-r002-l005-w006",
          "p006-b003-r002-l005-w007",
          "p006-b003-r002-l005-w008",
          "p006-b003-r002-l005-w009",
          "p006-b003-r002-l005-w010",
          "p006-b003-r002-l005-w011",
          "p006-b003-r002-l006-w001",
          "p006-b003-r002-l006-w002",
          "p006-b003-r002-l006-w003",
          "p006-b003-r002-l006-w004",
          "p006-b003-r002-l006-w005",
          "p006-b003-r002-l006-w006",
          "p006-b003-r002-l006-w008",
          "p006-b003-r002-l006-w009",
          "p006-b003-r002-l006-w010",
          "p006-b003-r002-l006-w011",
          "p006-b003-r002-l006-w012",
          "p006-b003-r002-l006-w013",
          "p006-b003-r002-l007-w001",
          "p006-b003-r002-l007-w002",
          "p006-b003-r002-l007-w003",
          "p006-b003-r002-l007-w004",
          "p006-b003-r002-l007-w005",
          "p006-b003-r002-l007-w006",
          "p006-b003-r002-l007-w007",
          "p006-b003-r002-l007-w008",
          "p006-b003-r002-l007-w009",
          "p006-b003-r002-l008-w001",
          "p006-b003-r002-l008-w002",
          "p006-b003-r002-l008-w003",
          "p006-b003-r002-l008-w004",
          "p006-b003-r002-l008-w005",
          "p006-b003-r002-l008-w006",
          "p006-b003-r002-l008-w007",
          "p006-b003-r002-l008-w008",
          "p006-b003-r002-l009-w001",
          "p006-b003-r002-l009-w002"
        ],
        "bbox": {
          "x": 351,
          "y": 839,
          "width": 893,
          "height": 330
        },
        "matched_tokens": 77,
        "total_tokens": 77
      },
      "type": "diary_entry",
      "date": {
        "date_source": "Nov. 16 - Monday",
        "date_normalized": null,
        "normalization_status": "not_normalized",
        "normalization_confidence": null,
        "normalization_reason": null
      },
      "place_source": null,
      "content": [
        {
          "id": "p006-b002-p001",
          "order": 1,
          "evidence": {
            "status": "not_attempted",
            "method": null,
            "ocr_word_ids": [],
            "bbox": null,
            "matched_tokens": 0,
            "total_tokens": 0
          },
          "type": "text",
          "role": "dateline",
          "lines": [
            {
              "line_number": 1,
              "segments": [
                {
                  "type": "text",
                  "text": "Nov. 16 - Monday"
                }
              ],
              "line_end": "block_end"
            }
          ]
        },
        {
          "id": "p006-b002-p002",
          "order": 2,
          "evidence": {
            "status": "not_attempted",
            "method": null,
            "ocr_word_ids": [],
            "bbox": null,
            "matched_tokens": 0,
            "total_tokens": 0
          },
          "type": "text",
          "role": "body",
          "lines": [
            {
              "line_number": 1,
              "segments": [
                {
                  "type": "text",
                  "text": "Rather late about arising  great preparations about"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 2,
              "segments": [
                {
                  "type": "text",
                  "text": "getting ready to land.  Drawing in toward Ireland."
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 3,
              "segments": [
                {
                  "type": "text",
                  "text": "Nothing of importance happened except I became much"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 4,
              "segments": [
                {
                  "type": "text",
                  "text": "interested in Miss Jennie Holland, and we had several"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 5,
              "segments": [
                {
                  "type": "text",
                  "text": "nice walks together.  I told her how I liked her and"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 6,
              "segments": [
                {
                  "type": "text",
                  "text": "How I hated to leave her - we were out until after 12"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 7,
              "segments": [
                {
                  "type": "text",
                  "text": "midnight and then I Packed my trunk and telescope"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 8,
              "segments": [
                {
                  "type": "text",
                  "text": "preparatory to landing at Queenstown at 3 o'clock"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 9,
              "segments": [
                {
                  "type": "text",
                  "text": "Tuesday morning."
                }
              ],
              "line_end": "block_end"
            }
          ]
        }
      ]
    },
    {
      "id": "p006-b003",
      "order": 3,
      "continuation": {
        "from_previous": "no",
        "to_next": "yes",
        "previous": null,
        "next": null
      },
      "evidence": {
        "status": "partial",
        "method": "exact_normalized_token_sequence",
        "ocr_word_ids": [
          "p006-b004-r001-l001-w001",
          "p006-b004-r001-l001-w002",
          "p006-b004-r001-l001-w004",
          "p006-b004-r002-l001-w001",
          "p006-b004-r002-l001-w002",
          "p006-b004-r002-l001-w003",
          "p006-b004-r002-l001-w004",
          "p006-b004-r002-l001-w006",
          "p006-b004-r002-l001-w007",
          "p006-b004-r002-l001-w008",
          "p006-b004-r002-l001-w009",
          "p006-b004-r002-l001-w010",
          "p006-b004-r002-l001-w011",
          "p006-b004-r002-l002-w001",
          "p006-b004-r002-l002-w002",
          "p006-b004-r002-l002-w003",
          "p006-b004-r002-l002-w004",
          "p006-b004-r002-l002-w005",
          "p006-b004-r002-l002-w006",
          "p006-b004-r002-l002-w007",
          "p006-b004-r002-l002-w008",
          "p006-b004-r002-l002-w009",
          "p006-b004-r002-l002-w010",
          "p006-b004-r002-l002-w011",
          "p006-b004-r002-l002-w012",
          "p006-b004-r002-l003-w001",
          "p006-b004-r002-l003-w002",
          "p006-b004-r002-l003-w003",
          "p006-b004-r002-l003-w004",
          "p006-b004-r002-l003-w005",
          "p006-b004-r002-l003-w006",
          "p006-b004-r002-l003-w007",
          "p006-b004-r002-l003-w008",
          "p006-b004-r002-l003-w009",
          "p006-b004-r002-l003-w010",
          "p006-b004-r002-l003-w011",
          "p006-b004-r002-l004-w001",
          "p006-b004-r002-l004-w002",
          "p006-b004-r002-l004-w003",
          "p006-b004-r002-l004-w004",
          "p006-b004-r002-l004-w005",
          "p006-b004-r002-l004-w006",
          "p006-b004-r002-l004-w007",
          "p006-b004-r002-l004-w008",
          "p006-b004-r002-l004-w009",
          "p006-b004-r002-l004-w010",
          "p006-b004-r002-l004-w011",
          "p006-b004-r002-l004-w012",
          "p006-b004-r002-l005-w001",
          "p006-b004-r002-l005-w002",
          "p006-b004-r002-l005-w003",
          "p006-b004-r002-l005-w004",
          "p006-b004-r002-l005-w005",
          "p006-b004-r002-l005-w006",
          "p006-b004-r002-l005-w007",
          "p006-b004-r002-l005-w008",
          "p006-b004-r002-l005-w009",
          "p006-b004-r002-l006-w001",
          "p006-b004-r002-l006-w002",
          "p006-b004-r002-l006-w003",
          "p006-b004-r002-l006-w004",
          "p006-b004-r002-l006-w005",
          "p006-b004-r002-l006-w006",
          "p006-b004-r002-l006-w007",
          "p006-b004-r002-l006-w008",
          "p006-b004-r002-l006-w009",
          "p006-b004-r002-l006-w010",
          "p006-b004-r002-l007-w001",
          "p006-b004-r002-l007-w002",
          "p006-b004-r002-l007-w003",
          "p006-b004-r002-l007-w004",
          "p006-b004-r002-l007-w005",
          "p006-b004-r002-l007-w006",
          "p006-b004-r002-l007-w007",
          "p006-b004-r002-l007-w008",
          "p006-b004-r002-l007-w009",
          "p006-b004-r002-l007-w010",
          "p006-b004-r002-l007-w011",
          "p006-b004-r002-l008-w001",
          "p006-b004-r002-l008-w002",
          "p006-b004-r002-l008-w003",
          "p006-b004-r002-l008-w004",
          "p006-b004-r002-l008-w005",
          "p006-b004-r002-l008-w006",
          "p006-b004-r002-l008-w007",
          "p006-b004-r002-l008-w008",
          "p006-b004-r002-l008-w009",
          "p006-b004-r002-l009-w001",
          "p006-b004-r002-l009-w002",
          "p006-b004-r002-l009-w003",
          "p006-b004-r002-l009-w004",
          "p006-b004-r002-l009-w005",
          "p006-b004-r002-l009-w006",
          "p006-b004-r002-l009-w007",
          "p006-b004-r002-l009-w008",
          "p006-b004-r002-l009-w009",
          "p006-b004-r002-l010-w001",
          "p006-b004-r002-l010-w002",
          "p006-b004-r002-l010-w003",
          "p006-b004-r002-l010-w004",
          "p006-b004-r002-l010-w005",
          "p006-b004-r002-l010-w006",
          "p006-b004-r002-l010-w007",
          "p006-b004-r002-l010-w008",
          "p006-b004-r002-l010-w009",
          "p006-b004-r002-l010-w010",
          "p006-b004-r002-l010-w011",
          "p006-b004-r002-l011-w001",
          "p006-b004-r002-l011-w002",
          "p006-b004-r002-l011-w003",
          "p006-b004-r002-l011-w004",
          "p006-b004-r002-l011-w005",
          "p006-b004-r002-l011-w006",
          "p006-b004-r002-l011-w007",
          "p006-b004-r002-l011-w008",
          "p006-b004-r002-l011-w009",
          "p006-b004-r002-l012-w001",
          "p006-b004-r002-l012-w002",
          "p006-b004-r002-l012-w003",
          "p006-b004-r002-l012-w004",
          "p006-b004-r002-l012-w005",
          "p006-b004-r002-l012-w006",
          "p006-b004-r002-l012-w007",
          "p006-b004-r002-l012-w008",
          "p006-b004-r002-l012-w009",
          "p006-b004-r002-l012-w010",
          "p006-b004-r002-l013-w001",
          "p006-b004-r002-l013-w002",
          "p006-b004-r002-l013-w003",
          "p006-b004-r002-l013-w005",
          "p006-b004-r002-l013-w006",
          "p006-b004-r002-l013-w007",
          "p006-b004-r002-l013-w008",
          "p006-b004-r002-l013-w009",
          "p006-b004-r002-l014-w001",
          "p006-b004-r002-l014-w002",
          "p006-b004-r002-l014-w003",
          "p006-b004-r002-l014-w004",
          "p006-b004-r002-l014-w005",
          "p006-b004-r002-l014-w006",
          "p006-b004-r002-l014-w007",
          "p006-b004-r002-l014-w008",
          "p006-b004-r002-l014-w009",
          "p006-b004-r002-l015-w001",
          "p006-b004-r002-l015-w002",
          "p006-b004-r002-l015-w004",
          "p006-b004-r002-l015-w005",
          "p006-b004-r002-l015-w006",
          "p006-b004-r002-l015-w007",
          "p006-b004-r002-l015-w008",
          "p006-b004-r002-l015-w009",
          "p006-b004-r002-l015-w010",
          "p006-b004-r002-l015-w011",
          "p006-b004-r002-l015-w012",
          "p006-b004-r002-l016-w001",
          "p006-b004-r002-l016-w002",
          "p006-b004-r002-l016-w003",
          "p006-b004-r002-l016-w004",
          "p006-b004-r002-l016-w005",
          "p006-b004-r002-l016-w006",
          "p006-b004-r002-l016-w007",
          "p006-b004-r002-l016-w008",
          "p006-b004-r002-l016-w009",
          "p006-b004-r002-l017-w001",
          "p006-b004-r002-l017-w002",
          "p006-b004-r002-l017-w004",
          "p006-b004-r002-l017-w005",
          "p006-b004-r002-l017-w006",
          "p006-b004-r002-l017-w007",
          "p006-b004-r002-l017-w008",
          "p006-b004-r002-l017-w009",
          "p006-b004-r002-l017-w010",
          "p006-b004-r002-l018-w001",
          "p006-b004-r002-l018-w002",
          "p006-b004-r002-l018-w003",
          "p006-b004-r002-l018-w004",
          "p006-b004-r002-l018-w005",
          "p006-b004-r002-l018-w006",
          "p006-b004-r002-l018-w007",
          "p006-b004-r002-l018-w008",
          "p006-b004-r002-l018-w009",
          "p006-b004-r002-l018-w010",
          "p006-b004-r002-l018-w011",
          "p006-b004-r002-l019-w001",
          "p006-b004-r002-l019-w002",
          "p006-b004-r002-l019-w003",
          "p006-b004-r002-l019-w004",
          "p006-b004-r002-l019-w005",
          "p006-b004-r002-l019-w006",
          "p006-b004-r002-l019-w007",
          "p006-b004-r002-l019-w008",
          "p006-b004-r002-l019-w009",
          "p006-b004-r002-l019-w010",
          "p006-b004-r002-l019-w011",
          "p006-b004-r002-l020-w001",
          "p006-b004-r002-l020-w002",
          "p006-b004-r002-l020-w003",
          "p006-b004-r002-l020-w004",
          "p006-b004-r002-l020-w005",
          "p006-b004-r002-l020-w006",
          "p006-b004-r002-l020-w007",
          "p006-b004-r002-l020-w008"
        ],
        "bbox": {
          "x": 353,
          "y": 1206,
          "width": 875,
          "height": 695
        },
        "matched_tokens": 203,
        "total_tokens": 207
      },
      "type": "diary_entry",
      "date": {
        "date_source": "Nov. 17 - Tuesday",
        "date_normalized": null,
        "normalization_status": "not_normalized",
        "normalization_confidence": null,
        "normalization_reason": null
      },
      "place_source": null,
      "content": [
        {
          "id": "p006-b003-p001",
          "order": 1,
          "evidence": {
            "status": "not_attempted",
            "method": null,
            "ocr_word_ids": [],
            "bbox": null,
            "matched_tokens": 0,
            "total_tokens": 0
          },
          "type": "text",
          "role": "dateline",
          "lines": [
            {
              "line_number": 1,
              "segments": [
                {
                  "type": "text",
                  "text": "Nov. 17 - Tuesday"
                }
              ],
              "line_end": "block_end"
            }
          ]
        },
        {
          "id": "p006-b003-p002",
          "order": 2,
          "evidence": {
            "status": "not_attempted",
            "method": null,
            "ocr_word_ids": [],
            "bbox": null,
            "matched_tokens": 0,
            "total_tokens": 0
          },
          "type": "text",
          "role": "body",
          "lines": [
            {
              "line_number": 1,
              "segments": [
                {
                  "type": "text",
                  "text": "At 4 o'clock this a.m. the steward called me to get"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 2,
              "segments": [
                {
                  "type": "text",
                  "text": "up and have some coffee as we were soon to stop at"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 3,
              "segments": [
                {
                  "type": "text",
                  "text": "Queenstown.  I got up and nearly all on board got up"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 4,
              "segments": [
                {
                  "type": "text",
                  "text": "to see those off who were going to land at Q.  But"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 5,
              "segments": [
                {
                  "type": "text",
                  "text": "something was wrong at the signal stations and the"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 6,
              "segments": [
                {
                  "type": "text",
                  "text": "tender (the boat on which we were unloaded) did not"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 7,
              "segments": [
                {
                  "type": "text",
                  "text": "get the news of our arrival so we anchored about 2"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 8,
              "segments": [
                {
                  "type": "text",
                  "text": "hours.  Miss H and myself had a nice pleasant time"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 9,
              "segments": [
                {
                  "type": "text",
                  "text": "walking and talking until the tender came.  I then"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 10,
              "segments": [
                {
                  "type": "text",
                  "text": "got on the tender and went up the Cork Harbor to"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 11,
              "segments": [
                {
                  "type": "text",
                  "text": "Queenstown about an hour's ride.  The water in the"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 12,
              "segments": [
                {
                  "type": "text",
                  "text": "harbor was very placid and as it was just getting"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 13,
              "segments": [
                {
                  "type": "text",
                  "text": "light the hills & garrisons on either side looked"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 14,
              "segments": [
                {
                  "type": "text",
                  "text": "beautiful.  The scenery is grand.  We arrived at Q."
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 15,
              "segments": [
                {
                  "type": "text",
                  "text": "at 7 a.m. I together with a lot of others, and went"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 16,
              "segments": [
                {
                  "type": "text",
                  "text": "into the Custom House and had our packages opened"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 17,
              "segments": [
                {
                  "type": "text",
                  "text": "and inspected - no goods which were subject to duty,"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 18,
              "segments": [
                {
                  "type": "text",
                  "text": "except a box of cigars which I was careful to take"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 19,
              "segments": [
                {
                  "type": "text",
                  "text": "out of the box and put in my overcoat pocket.  I"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 20,
              "segments": [
                {
                  "type": "text",
                  "text": "then went uptown with Mrs. Abraham, the Garrigan"
                }
              ],
              "line_end": "no_hyphen"
            }
          ]
        }
      ]
    }
  ],
  "editorial_notes": [],
  "provenance": {
    "pipeline_version": "0.1.0",
    "model_run_id": "20260808T180301Z-eval",
    "backend": "codex-exec",
    "model": "gpt-5.6-sol",
    "reasoning_effort": "xhigh",
    "prompt_sha256": "eebd92ab915971f497854ea2d36d9fc8ca91724afad55242695e4ad5d80e966a",
    "schema_sha256": "a1c29dca3f75ac07c6939242f315bb53cac9c82f75ce42df8aa1c4721bf9f056",
    "candidate_sha256": "ba4e0b14400a625d040404afba5ce910c7ea781de286ad935075d542ce31585f",
    "context_pages": [
      5,
      7
    ],
    "steps": [
      {
        "kind": "ocr",
        "actor": "tesseract 5.5.0",
        "artifact": "ocr/page-006.txt",
        "created_at": "2026-08-08T18:03:49Z"
      },
      {
        "kind": "model_transcription",
        "actor": "codex-exec:gpt-5.6-sol",
        "artifact": "20260808T180301Z-eval",
        "created_at": "2026-08-08T18:03:49Z"
      }
    ]
  },
  "review": {
    "status": "model_candidate",
    "authority": "diagnostic_only",
    "reviewer": null,
    "reviewed_at": null,
    "notes": [
      "Model candidate only; the page image remains authoritative."
    ]
  }
}
Agent-reviewed diagnostic JSON

open or download JSON

{
  "schema_version": "1.1.0",
  "page_id": "page-006",
  "source": {
    "pdf_page": 6,
    "source_pdf_sha256": "80a074ed94fded84fa8a455d61fbf94b25cd4f1239d5ec3e639aaf443467c53f",
    "image": {
      "path": "pages/page-006.png",
      "sha256": "54324af70b4ce807f7bdde2a88446d7bbd3fa46aacf95d87c55db521cba05e10",
      "width": 1700,
      "height": 2200,
      "dpi": 200
    },
    "ocr": {
      "text_path": "ocr/page-006.txt",
      "text_sha256": "c43acc671cbe2c1f386b948a4c229bd03821071d0ea9ff94b1a545d8451acda0",
      "tsv_path": "ocr/page-006.tsv",
      "tsv_sha256": "869b2b51411feb1ebf78b23a45b0ceb5a29389f55d1f32f9dffeec18ba8f7e2e",
      "engine": "tesseract 5.5.0"
    }
  },
  "segment": {
    "id": "book-01",
    "kind": "book",
    "label_source": "First book",
    "assignment_status": "inferred"
  },
  "page_role": "content",
  "boundary": {
    "starts_mid_block": "yes",
    "ends_mid_block": "yes"
  },
  "blocks": [
    {
      "id": "p006-b001",
      "order": 1,
      "continuation": {
        "from_previous": "yes",
        "to_next": "no",
        "previous": null,
        "next": null
      },
      "evidence": {
        "status": "partial",
        "method": "exact_normalized_token_sequence",
        "ocr_word_ids": [
          "p006-b001-r001-l001-w001",
          "p006-b001-r001-l001-w002",
          "p006-b001-r001-l001-w003",
          "p006-b001-r001-l001-w004",
          "p006-b001-r001-l001-w005",
          "p006-b001-r001-l001-w006",
          "p006-b001-r001-l001-w007",
          "p006-b001-r001-l001-w008",
          "p006-b001-r001-l001-w009",
          "p006-b001-r001-l002-w001",
          "p006-b001-r001-l002-w002",
          "p006-b001-r001-l002-w003",
          "p006-b001-r001-l002-w004",
          "p006-b001-r001-l002-w005",
          "p006-b001-r001-l002-w006",
          "p006-b001-r001-l002-w007",
          "p006-b001-r001-l003-w002",
          "p006-b001-r001-l003-w003",
          "p006-b001-r001-l003-w004",
          "p006-b001-r001-l003-w005",
          "p006-b001-r001-l003-w006",
          "p006-b001-r001-l003-w007",
          "p006-b001-r001-l003-w008",
          "p006-b001-r001-l003-w009",
          "p006-b001-r001-l003-w010",
          "p006-b001-r001-l003-w011",
          "p006-b001-r001-l004-w001",
          "p006-b001-r001-l004-w002",
          "p006-b001-r001-l004-w003",
          "p006-b001-r001-l004-w004",
          "p006-b001-r001-l004-w005",
          "p006-b001-r001-l004-w006",
          "p006-b001-r001-l004-w007",
          "p006-b001-r001-l004-w008",
          "p006-b001-r001-l004-w009",
          "p006-b001-r001-l004-w010",
          "p006-b001-r001-l004-w011",
          "p006-b001-r001-l004-w012",
          "p006-b001-r001-l005-w001",
          "p006-b001-r001-l005-w003",
          "p006-b001-r001-l005-w004",
          "p006-b001-r001-l005-w005",
          "p006-b001-r001-l005-w006",
          "p006-b001-r001-l005-w007",
          "p006-b001-r001-l005-w008",
          "p006-b001-r001-l005-w009",
          "p006-b001-r001-l005-w010",
          "p006-b001-r001-l005-w011",
          "p006-b001-r001-l005-w012",
          "p006-b001-r001-l006-w001",
          "p006-b001-r001-l006-w002",
          "p006-b001-r001-l006-w003",
          "p006-b001-r001-l006-w004",
          "p006-b001-r001-l006-w005",
          "p006-b001-r001-l006-w006",
          "p006-b001-r001-l006-w007",
          "p006-b001-r001-l006-w008",
          "p006-b001-r001-l006-w009",
          "p006-b001-r001-l006-w010",
          "p006-b001-r001-l006-w011",
          "p006-b001-r001-l007-w001",
          "p006-b001-r001-l007-w002",
          "p006-b001-r001-l007-w003",
          "p006-b001-r001-l007-w004",
          "p006-b001-r001-l007-w005",
          "p006-b001-r001-l007-w006",
          "p006-b001-r001-l007-w007",
          "p006-b001-r001-l007-w008",
          "p006-b001-r001-l007-w009",
          "p006-b001-r001-l008-w002",
          "p006-b001-r001-l008-w003",
          "p006-b001-r001-l008-w004",
          "p006-b001-r001-l008-w005",
          "p006-b001-r001-l008-w006",
          "p006-b001-r001-l008-w007",
          "p006-b001-r001-l008-w008",
          "p006-b001-r001-l008-w009",
          "p006-b001-r001-l008-w010",
          "p006-b001-r001-l008-w011",
          "p006-b001-r001-l008-w012",
          "p006-b001-r001-l008-w013",
          "p006-b001-r001-l008-w014",
          "p006-b001-r001-l009-w001",
          "p006-b001-r001-l009-w002",
          "p006-b001-r001-l009-w003",
          "p006-b001-r001-l009-w004",
          "p006-b001-r001-l009-w005",
          "p006-b001-r001-l009-w006",
          "p006-b001-r001-l009-w007",
          "p006-b001-r001-l009-w008",
          "p006-b001-r001-l009-w009",
          "p006-b001-r001-l009-w010",
          "p006-b001-r001-l009-w011",
          "p006-b001-r001-l010-w002",
          "p006-b001-r001-l010-w003",
          "p006-b001-r001-l010-w005",
          "p006-b001-r001-l010-w006",
          "p006-b001-r001-l010-w007",
          "p006-b001-r001-l010-w008",
          "p006-b001-r001-l010-w009",
          "p006-b001-r001-l010-w010",
          "p006-b001-r001-l010-w011",
          "p006-b001-r001-l010-w012",
          "p006-b002-r001-l001-w001",
          "p006-b002-r001-l001-w002",
          "p006-b002-r001-l001-w003",
          "p006-b002-r001-l001-w004",
          "p006-b002-r001-l001-w005",
          "p006-b002-r001-l001-w006",
          "p006-b002-r001-l001-w008",
          "p006-b002-r001-l001-w009",
          "p006-b002-r001-l001-w010",
          "p006-b002-r001-l001-w011",
          "p006-b002-r001-l002-w001"
        ],
        "bbox": {
          "x": 350,
          "y": 406,
          "width": 925,
          "height": 391
        },
        "matched_tokens": 114,
        "total_tokens": 117
      },
      "type": "diary_entry",
      "date": null,
      "place_source": null,
      "content": [
        {
          "id": "p006-b001-p001",
          "order": 1,
          "evidence": {
            "status": "not_attempted",
            "method": null,
            "ocr_word_ids": [],
            "bbox": null,
            "matched_tokens": 0,
            "total_tokens": 0
          },
          "type": "text",
          "role": "body",
          "lines": [
            {
              "line_number": 1,
              "segments": [
                {
                  "type": "text",
                  "text": "Thanks to our Heavenly Father.  The day was spent"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 2,
              "segments": [
                {
                  "type": "text",
                  "text": "pleasantly, by reading and conversation, and after"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 3,
              "segments": [
                {
                  "type": "text",
                  "text": "\"tea\" just before the song service I went in with Miss"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 4,
              "segments": [
                {
                  "type": "text",
                  "text": "Slater and had a nice talk with her sister who is very"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 5,
              "segments": [
                {
                  "type": "text",
                  "text": "ill - we had prayer and came out to the song service."
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 6,
              "segments": [
                {
                  "type": "text",
                  "text": "After which a little walk on deck, and down in the"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 7,
              "segments": [
                {
                  "type": "text",
                  "text": "saloon again while I am writing, Miss Holland is punch"
                }
              ],
              "line_end": "hyphen_word_break"
            },
            {
              "line_number": 8,
              "segments": [
                {
                  "type": "text",
                  "text": "ing my hand with a long pole.  I am at a table with a"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 9,
              "segments": [
                {
                  "type": "text",
                  "text": "lot of English men and women.  Now the steward says it"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 10,
              "segments": [
                {
                  "type": "text",
                  "text": "is eleven o'clock & shuts off the lights so I retire to"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 11,
              "segments": [
                {
                  "type": "text",
                  "text": "my state room and Mr. Morrison & myself eat an apple"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 12,
              "segments": [
                {
                  "type": "text",
                  "text": "each."
                }
              ],
              "line_end": "block_end"
            }
          ]
        }
      ]
    },
    {
      "id": "p006-b002",
      "order": 2,
      "continuation": {
        "from_previous": "no",
        "to_next": "no",
        "previous": null,
        "next": null
      },
      "evidence": {
        "status": "aligned",
        "method": "exact_normalized_token_sequence",
        "ocr_word_ids": [
          "p006-b003-r001-l001-w001",
          "p006-b003-r001-l001-w002",
          "p006-b003-r001-l001-w004",
          "p006-b003-r002-l001-w001",
          "p006-b003-r002-l001-w002",
          "p006-b003-r002-l001-w003",
          "p006-b003-r002-l001-w004",
          "p006-b003-r002-l001-w005",
          "p006-b003-r002-l001-w006",
          "p006-b003-r002-l001-w007",
          "p006-b003-r002-l002-w001",
          "p006-b003-r002-l002-w002",
          "p006-b003-r002-l002-w003",
          "p006-b003-r002-l002-w004",
          "p006-b003-r002-l002-w005",
          "p006-b003-r002-l002-w006",
          "p006-b003-r002-l002-w007",
          "p006-b003-r002-l002-w008",
          "p006-b003-r002-l003-w001",
          "p006-b003-r002-l003-w002",
          "p006-b003-r002-l003-w003",
          "p006-b003-r002-l003-w004",
          "p006-b003-r002-l003-w005",
          "p006-b003-r002-l003-w006",
          "p006-b003-r002-l003-w007",
          "p006-b003-r002-l003-w008",
          "p006-b003-r002-l004-w001",
          "p006-b003-r002-l004-w002",
          "p006-b003-r002-l004-w003",
          "p006-b003-r002-l004-w004",
          "p006-b003-r002-l004-w005",
          "p006-b003-r002-l004-w006",
          "p006-b003-r002-l004-w007",
          "p006-b003-r002-l004-w008",
          "p006-b003-r002-l004-w009",
          "p006-b003-r002-l005-w001",
          "p006-b003-r002-l005-w002",
          "p006-b003-r002-l005-w003",
          "p006-b003-r002-l005-w004",
          "p006-b003-r002-l005-w005",
          "p006-b003-r002-l005-w006",
          "p006-b003-r002-l005-w007",
          "p006-b003-r002-l005-w008",
          "p006-b003-r002-l005-w009",
          "p006-b003-r002-l005-w010",
          "p006-b003-r002-l005-w011",
          "p006-b003-r002-l006-w001",
          "p006-b003-r002-l006-w002",
          "p006-b003-r002-l006-w003",
          "p006-b003-r002-l006-w004",
          "p006-b003-r002-l006-w005",
          "p006-b003-r002-l006-w006",
          "p006-b003-r002-l006-w008",
          "p006-b003-r002-l006-w009",
          "p006-b003-r002-l006-w010",
          "p006-b003-r002-l006-w011",
          "p006-b003-r002-l006-w012",
          "p006-b003-r002-l006-w013",
          "p006-b003-r002-l007-w001",
          "p006-b003-r002-l007-w002",
          "p006-b003-r002-l007-w003",
          "p006-b003-r002-l007-w004",
          "p006-b003-r002-l007-w005",
          "p006-b003-r002-l007-w006",
          "p006-b003-r002-l007-w007",
          "p006-b003-r002-l007-w008",
          "p006-b003-r002-l007-w009",
          "p006-b003-r002-l008-w001",
          "p006-b003-r002-l008-w002",
          "p006-b003-r002-l008-w003",
          "p006-b003-r002-l008-w004",
          "p006-b003-r002-l008-w005",
          "p006-b003-r002-l008-w006",
          "p006-b003-r002-l008-w007",
          "p006-b003-r002-l008-w008",
          "p006-b003-r002-l009-w001",
          "p006-b003-r002-l009-w002"
        ],
        "bbox": {
          "x": 351,
          "y": 839,
          "width": 893,
          "height": 330
        },
        "matched_tokens": 77,
        "total_tokens": 77
      },
      "type": "diary_entry",
      "date": {
        "date_source": "Nov. 16 - Monday",
        "date_normalized": null,
        "normalization_status": "not_normalized",
        "normalization_confidence": null,
        "normalization_reason": null
      },
      "place_source": null,
      "content": [
        {
          "id": "p006-b002-p001",
          "order": 1,
          "evidence": {
            "status": "not_attempted",
            "method": null,
            "ocr_word_ids": [],
            "bbox": null,
            "matched_tokens": 0,
            "total_tokens": 0
          },
          "type": "text",
          "role": "dateline",
          "lines": [
            {
              "line_number": 1,
              "segments": [
                {
                  "type": "text",
                  "text": "Nov. 16 - Monday"
                }
              ],
              "line_end": "block_end"
            }
          ]
        },
        {
          "id": "p006-b002-p002",
          "order": 2,
          "evidence": {
            "status": "not_attempted",
            "method": null,
            "ocr_word_ids": [],
            "bbox": null,
            "matched_tokens": 0,
            "total_tokens": 0
          },
          "type": "text",
          "role": "body",
          "lines": [
            {
              "line_number": 1,
              "segments": [
                {
                  "type": "text",
                  "text": "Rather late about arising  great preparations about"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 2,
              "segments": [
                {
                  "type": "text",
                  "text": "getting ready to land.  Drawing in toward Ireland."
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 3,
              "segments": [
                {
                  "type": "text",
                  "text": "Nothing of importance happened except I became much"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 4,
              "segments": [
                {
                  "type": "text",
                  "text": "interested in Miss Jennie Holland, and we had several"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 5,
              "segments": [
                {
                  "type": "text",
                  "text": "nice walks together.  I told her how I liked her and"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 6,
              "segments": [
                {
                  "type": "text",
                  "text": "How I hated to leave her - we were out until after 12"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 7,
              "segments": [
                {
                  "type": "text",
                  "text": "midnight and then I Packed my trunk and telescope"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 8,
              "segments": [
                {
                  "type": "text",
                  "text": "preparatory to landing at Queenstown at 3 o'clock"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 9,
              "segments": [
                {
                  "type": "text",
                  "text": "Tuesday morning."
                }
              ],
              "line_end": "block_end"
            }
          ]
        }
      ]
    },
    {
      "id": "p006-b003",
      "order": 3,
      "continuation": {
        "from_previous": "no",
        "to_next": "yes",
        "previous": null,
        "next": null
      },
      "evidence": {
        "status": "partial",
        "method": "exact_normalized_token_sequence",
        "ocr_word_ids": [
          "p006-b004-r001-l001-w001",
          "p006-b004-r001-l001-w002",
          "p006-b004-r001-l001-w004",
          "p006-b004-r002-l001-w001",
          "p006-b004-r002-l001-w002",
          "p006-b004-r002-l001-w003",
          "p006-b004-r002-l001-w004",
          "p006-b004-r002-l001-w006",
          "p006-b004-r002-l001-w007",
          "p006-b004-r002-l001-w008",
          "p006-b004-r002-l001-w009",
          "p006-b004-r002-l001-w010",
          "p006-b004-r002-l001-w011",
          "p006-b004-r002-l002-w001",
          "p006-b004-r002-l002-w002",
          "p006-b004-r002-l002-w003",
          "p006-b004-r002-l002-w004",
          "p006-b004-r002-l002-w005",
          "p006-b004-r002-l002-w006",
          "p006-b004-r002-l002-w007",
          "p006-b004-r002-l002-w008",
          "p006-b004-r002-l002-w009",
          "p006-b004-r002-l002-w010",
          "p006-b004-r002-l002-w011",
          "p006-b004-r002-l002-w012",
          "p006-b004-r002-l003-w001",
          "p006-b004-r002-l003-w002",
          "p006-b004-r002-l003-w003",
          "p006-b004-r002-l003-w004",
          "p006-b004-r002-l003-w005",
          "p006-b004-r002-l003-w006",
          "p006-b004-r002-l003-w007",
          "p006-b004-r002-l003-w008",
          "p006-b004-r002-l003-w009",
          "p006-b004-r002-l003-w010",
          "p006-b004-r002-l003-w011",
          "p006-b004-r002-l004-w001",
          "p006-b004-r002-l004-w002",
          "p006-b004-r002-l004-w003",
          "p006-b004-r002-l004-w004",
          "p006-b004-r002-l004-w005",
          "p006-b004-r002-l004-w006",
          "p006-b004-r002-l004-w007",
          "p006-b004-r002-l004-w008",
          "p006-b004-r002-l004-w009",
          "p006-b004-r002-l004-w010",
          "p006-b004-r002-l004-w011",
          "p006-b004-r002-l004-w012",
          "p006-b004-r002-l005-w001",
          "p006-b004-r002-l005-w002",
          "p006-b004-r002-l005-w003",
          "p006-b004-r002-l005-w004",
          "p006-b004-r002-l005-w005",
          "p006-b004-r002-l005-w006",
          "p006-b004-r002-l005-w007",
          "p006-b004-r002-l005-w008",
          "p006-b004-r002-l005-w009",
          "p006-b004-r002-l006-w001",
          "p006-b004-r002-l006-w002",
          "p006-b004-r002-l006-w003",
          "p006-b004-r002-l006-w004",
          "p006-b004-r002-l006-w005",
          "p006-b004-r002-l006-w006",
          "p006-b004-r002-l006-w007",
          "p006-b004-r002-l006-w008",
          "p006-b004-r002-l006-w009",
          "p006-b004-r002-l006-w010",
          "p006-b004-r002-l007-w001",
          "p006-b004-r002-l007-w002",
          "p006-b004-r002-l007-w003",
          "p006-b004-r002-l007-w004",
          "p006-b004-r002-l007-w005",
          "p006-b004-r002-l007-w006",
          "p006-b004-r002-l007-w007",
          "p006-b004-r002-l007-w008",
          "p006-b004-r002-l007-w009",
          "p006-b004-r002-l007-w010",
          "p006-b004-r002-l007-w011",
          "p006-b004-r002-l008-w001",
          "p006-b004-r002-l008-w002",
          "p006-b004-r002-l008-w003",
          "p006-b004-r002-l008-w004",
          "p006-b004-r002-l008-w005",
          "p006-b004-r002-l008-w006",
          "p006-b004-r002-l008-w007",
          "p006-b004-r002-l008-w008",
          "p006-b004-r002-l008-w009",
          "p006-b004-r002-l009-w001",
          "p006-b004-r002-l009-w002",
          "p006-b004-r002-l009-w003",
          "p006-b004-r002-l009-w004",
          "p006-b004-r002-l009-w005",
          "p006-b004-r002-l009-w006",
          "p006-b004-r002-l009-w007",
          "p006-b004-r002-l009-w008",
          "p006-b004-r002-l009-w009",
          "p006-b004-r002-l010-w001",
          "p006-b004-r002-l010-w002",
          "p006-b004-r002-l010-w003",
          "p006-b004-r002-l010-w004",
          "p006-b004-r002-l010-w005",
          "p006-b004-r002-l010-w006",
          "p006-b004-r002-l010-w007",
          "p006-b004-r002-l010-w008",
          "p006-b004-r002-l010-w009",
          "p006-b004-r002-l010-w010",
          "p006-b004-r002-l010-w011",
          "p006-b004-r002-l011-w001",
          "p006-b004-r002-l011-w002",
          "p006-b004-r002-l011-w003",
          "p006-b004-r002-l011-w004",
          "p006-b004-r002-l011-w005",
          "p006-b004-r002-l011-w006",
          "p006-b004-r002-l011-w007",
          "p006-b004-r002-l011-w008",
          "p006-b004-r002-l011-w009",
          "p006-b004-r002-l012-w001",
          "p006-b004-r002-l012-w002",
          "p006-b004-r002-l012-w003",
          "p006-b004-r002-l012-w004",
          "p006-b004-r002-l012-w005",
          "p006-b004-r002-l012-w006",
          "p006-b004-r002-l012-w007",
          "p006-b004-r002-l012-w008",
          "p006-b004-r002-l012-w009",
          "p006-b004-r002-l012-w010",
          "p006-b004-r002-l013-w001",
          "p006-b004-r002-l013-w002",
          "p006-b004-r002-l013-w003",
          "p006-b004-r002-l013-w005",
          "p006-b004-r002-l013-w006",
          "p006-b004-r002-l013-w007",
          "p006-b004-r002-l013-w008",
          "p006-b004-r002-l013-w009",
          "p006-b004-r002-l014-w001",
          "p006-b004-r002-l014-w002",
          "p006-b004-r002-l014-w003",
          "p006-b004-r002-l014-w004",
          "p006-b004-r002-l014-w005",
          "p006-b004-r002-l014-w006",
          "p006-b004-r002-l014-w007",
          "p006-b004-r002-l014-w008",
          "p006-b004-r002-l014-w009",
          "p006-b004-r002-l015-w001",
          "p006-b004-r002-l015-w002",
          "p006-b004-r002-l015-w004",
          "p006-b004-r002-l015-w005",
          "p006-b004-r002-l015-w006",
          "p006-b004-r002-l015-w007",
          "p006-b004-r002-l015-w008",
          "p006-b004-r002-l015-w009",
          "p006-b004-r002-l015-w010",
          "p006-b004-r002-l015-w011",
          "p006-b004-r002-l015-w012",
          "p006-b004-r002-l016-w001",
          "p006-b004-r002-l016-w002",
          "p006-b004-r002-l016-w003",
          "p006-b004-r002-l016-w004",
          "p006-b004-r002-l016-w005",
          "p006-b004-r002-l016-w006",
          "p006-b004-r002-l016-w007",
          "p006-b004-r002-l016-w008",
          "p006-b004-r002-l016-w009",
          "p006-b004-r002-l017-w001",
          "p006-b004-r002-l017-w002",
          "p006-b004-r002-l017-w004",
          "p006-b004-r002-l017-w005",
          "p006-b004-r002-l017-w006",
          "p006-b004-r002-l017-w007",
          "p006-b004-r002-l017-w008",
          "p006-b004-r002-l017-w009",
          "p006-b004-r002-l017-w010",
          "p006-b004-r002-l018-w001",
          "p006-b004-r002-l018-w002",
          "p006-b004-r002-l018-w003",
          "p006-b004-r002-l018-w004",
          "p006-b004-r002-l018-w005",
          "p006-b004-r002-l018-w006",
          "p006-b004-r002-l018-w007",
          "p006-b004-r002-l018-w008",
          "p006-b004-r002-l018-w009",
          "p006-b004-r002-l018-w010",
          "p006-b004-r002-l018-w011",
          "p006-b004-r002-l019-w001",
          "p006-b004-r002-l019-w002",
          "p006-b004-r002-l019-w003",
          "p006-b004-r002-l019-w004",
          "p006-b004-r002-l019-w005",
          "p006-b004-r002-l019-w006",
          "p006-b004-r002-l019-w007",
          "p006-b004-r002-l019-w008",
          "p006-b004-r002-l019-w009",
          "p006-b004-r002-l019-w010",
          "p006-b004-r002-l019-w011",
          "p006-b004-r002-l020-w001",
          "p006-b004-r002-l020-w002",
          "p006-b004-r002-l020-w003",
          "p006-b004-r002-l020-w004",
          "p006-b004-r002-l020-w005",
          "p006-b004-r002-l020-w006",
          "p006-b004-r002-l020-w007",
          "p006-b004-r002-l020-w008"
        ],
        "bbox": {
          "x": 353,
          "y": 1206,
          "width": 875,
          "height": 695
        },
        "matched_tokens": 203,
        "total_tokens": 207
      },
      "type": "diary_entry",
      "date": {
        "date_source": "Nov. 17 - Tuesday",
        "date_normalized": null,
        "normalization_status": "not_normalized",
        "normalization_confidence": null,
        "normalization_reason": null
      },
      "place_source": null,
      "content": [
        {
          "id": "p006-b003-p001",
          "order": 1,
          "evidence": {
            "status": "not_attempted",
            "method": null,
            "ocr_word_ids": [],
            "bbox": null,
            "matched_tokens": 0,
            "total_tokens": 0
          },
          "type": "text",
          "role": "dateline",
          "lines": [
            {
              "line_number": 1,
              "segments": [
                {
                  "type": "text",
                  "text": "Nov. 17 - Tuesday"
                }
              ],
              "line_end": "block_end"
            }
          ]
        },
        {
          "id": "p006-b003-p002",
          "order": 2,
          "evidence": {
            "status": "not_attempted",
            "method": null,
            "ocr_word_ids": [],
            "bbox": null,
            "matched_tokens": 0,
            "total_tokens": 0
          },
          "type": "text",
          "role": "body",
          "lines": [
            {
              "line_number": 1,
              "segments": [
                {
                  "type": "text",
                  "text": "At 4 o'clock this a.m. the steward called me to get"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 2,
              "segments": [
                {
                  "type": "text",
                  "text": "up and have some coffee as we were soon to stop at"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 3,
              "segments": [
                {
                  "type": "text",
                  "text": "Queenstown.  I got up and nearly all on board got up"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 4,
              "segments": [
                {
                  "type": "text",
                  "text": "to see those off who were going to land at Q.  But"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 5,
              "segments": [
                {
                  "type": "text",
                  "text": "something was wrong at the signal stations and the"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 6,
              "segments": [
                {
                  "type": "text",
                  "text": "tender (the boat on which we were unloaded) did not"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 7,
              "segments": [
                {
                  "type": "text",
                  "text": "get the news of our arrival so we anchored about 2"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 8,
              "segments": [
                {
                  "type": "text",
                  "text": "hours.  Miss H and myself had a nice-pleasant time"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 9,
              "segments": [
                {
                  "type": "text",
                  "text": "walking and talking until the tender came.  I then"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 10,
              "segments": [
                {
                  "type": "text",
                  "text": "got on the tender and went up the Cork Harbor to"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 11,
              "segments": [
                {
                  "type": "text",
                  "text": "Queenstown about an hour's ride.  The water in the"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 12,
              "segments": [
                {
                  "type": "text",
                  "text": "harbor was very placid and as it was just getting"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 13,
              "segments": [
                {
                  "type": "text",
                  "text": "light the hills & garrisons on either side looked"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 14,
              "segments": [
                {
                  "type": "text",
                  "text": "beautiful.  The scenery is grand.  We arrived at Q."
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 15,
              "segments": [
                {
                  "type": "text",
                  "text": "at 7 a.m. I together with a lot of others, and went"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 16,
              "segments": [
                {
                  "type": "text",
                  "text": "into the Custom House and had our packages opened"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 17,
              "segments": [
                {
                  "type": "text",
                  "text": "and inspected - no goods which were subject to duty,"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 18,
              "segments": [
                {
                  "type": "text",
                  "text": "except a box of cigars which I was careful to take"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 19,
              "segments": [
                {
                  "type": "text",
                  "text": "out of the box and put in my overcoat pocket.  I"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 20,
              "segments": [
                {
                  "type": "text",
                  "text": "then went uptown with Mrs. Abraham, the Garrigan"
                }
              ],
              "line_end": "no_hyphen"
            }
          ]
        }
      ]
    }
  ],
  "editorial_notes": [],
  "provenance": {
    "pipeline_version": "0.1.0",
    "model_run_id": "20260808T180301Z-eval",
    "backend": "codex-exec",
    "model": "gpt-5.6-sol",
    "reasoning_effort": "xhigh",
    "prompt_sha256": "eebd92ab915971f497854ea2d36d9fc8ca91724afad55242695e4ad5d80e966a",
    "schema_sha256": "a1c29dca3f75ac07c6939242f315bb53cac9c82f75ce42df8aa1c4721bf9f056",
    "candidate_sha256": "ba4e0b14400a625d040404afba5ce910c7ea781de286ad935075d542ce31585f",
    "context_pages": [
      5,
      7
    ],
    "steps": [
      {
        "kind": "ocr",
        "actor": "tesseract 5.5.0",
        "artifact": "ocr/page-006.txt",
        "created_at": "2026-08-08T18:03:49Z"
      },
      {
        "kind": "model_transcription",
        "actor": "codex-exec:gpt-5.6-sol",
        "artifact": "20260808T180301Z-eval",
        "created_at": "2026-08-08T18:03:49Z"
      },
      {
        "kind": "agent_review",
        "actor": "Codex",
        "artifact": "artifacts/runs/20260808T180301Z-eval/candidates/page-006.json",
        "created_at": "2026-08-08T18:09:26Z"
      }
    ]
  },
  "review": {
    "status": "agent_reviewed",
    "authority": "diagnostic_only",
    "reviewer": "Codex",
    "reviewed_at": "2026-08-08T18:09:26Z",
    "notes": [
      "Diagnostic fixture only; it is not independent ground truth and has not been owner-approved.",
      "Compared the complete page transcription with the authoritative page image.",
      "Corrected the visibly intentional source hyphen in nice-pleasant; the model had silently omitted it."
    ]
  }
}
Owner-approved edition JSON

open JSON

{
  "schema_version": "1.1.0",
  "page_id": "page-006",
  "source": {
    "pdf_page": 6,
    "source_pdf_sha256": "80a074ed94fded84fa8a455d61fbf94b25cd4f1239d5ec3e639aaf443467c53f",
    "image": {
      "path": "pages/page-006.png",
      "sha256": "54324af70b4ce807f7bdde2a88446d7bbd3fa46aacf95d87c55db521cba05e10",
      "width": 1700,
      "height": 2200,
      "dpi": 200
    },
    "ocr": {
      "text_path": "ocr/page-006.txt",
      "text_sha256": "c43acc671cbe2c1f386b948a4c229bd03821071d0ea9ff94b1a545d8451acda0",
      "tsv_path": "ocr/page-006.tsv",
      "tsv_sha256": "869b2b51411feb1ebf78b23a45b0ceb5a29389f55d1f32f9dffeec18ba8f7e2e",
      "engine": "tesseract 5.5.0"
    }
  },
  "segment": {
    "id": "book-01",
    "kind": "book",
    "label_source": "First book",
    "assignment_status": "inferred"
  },
  "page_role": "content",
  "boundary": {
    "starts_mid_block": "yes",
    "ends_mid_block": "yes"
  },
  "blocks": [
    {
      "id": "p006-b001",
      "order": 1,
      "continuation": {
        "from_previous": "yes",
        "to_next": "no",
        "previous": null,
        "next": null
      },
      "evidence": {
        "status": "partial",
        "method": "exact_normalized_token_sequence",
        "ocr_word_ids": [
          "p006-b001-r001-l001-w001",
          "p006-b001-r001-l001-w002",
          "p006-b001-r001-l001-w003",
          "p006-b001-r001-l001-w004",
          "p006-b001-r001-l001-w005",
          "p006-b001-r001-l001-w006",
          "p006-b001-r001-l001-w007",
          "p006-b001-r001-l001-w008",
          "p006-b001-r001-l001-w009",
          "p006-b001-r001-l002-w001",
          "p006-b001-r001-l002-w002",
          "p006-b001-r001-l002-w003",
          "p006-b001-r001-l002-w004",
          "p006-b001-r001-l002-w005",
          "p006-b001-r001-l002-w006",
          "p006-b001-r001-l002-w007",
          "p006-b001-r001-l003-w002",
          "p006-b001-r001-l003-w003",
          "p006-b001-r001-l003-w004",
          "p006-b001-r001-l003-w005",
          "p006-b001-r001-l003-w006",
          "p006-b001-r001-l003-w007",
          "p006-b001-r001-l003-w008",
          "p006-b001-r001-l003-w009",
          "p006-b001-r001-l003-w010",
          "p006-b001-r001-l003-w011",
          "p006-b001-r001-l004-w001",
          "p006-b001-r001-l004-w002",
          "p006-b001-r001-l004-w003",
          "p006-b001-r001-l004-w004",
          "p006-b001-r001-l004-w005",
          "p006-b001-r001-l004-w006",
          "p006-b001-r001-l004-w007",
          "p006-b001-r001-l004-w008",
          "p006-b001-r001-l004-w009",
          "p006-b001-r001-l004-w010",
          "p006-b001-r001-l004-w011",
          "p006-b001-r001-l004-w012",
          "p006-b001-r001-l005-w001",
          "p006-b001-r001-l005-w003",
          "p006-b001-r001-l005-w004",
          "p006-b001-r001-l005-w005",
          "p006-b001-r001-l005-w006",
          "p006-b001-r001-l005-w007",
          "p006-b001-r001-l005-w008",
          "p006-b001-r001-l005-w009",
          "p006-b001-r001-l005-w010",
          "p006-b001-r001-l005-w011",
          "p006-b001-r001-l005-w012",
          "p006-b001-r001-l006-w001",
          "p006-b001-r001-l006-w002",
          "p006-b001-r001-l006-w003",
          "p006-b001-r001-l006-w004",
          "p006-b001-r001-l006-w005",
          "p006-b001-r001-l006-w006",
          "p006-b001-r001-l006-w007",
          "p006-b001-r001-l006-w008",
          "p006-b001-r001-l006-w009",
          "p006-b001-r001-l006-w010",
          "p006-b001-r001-l006-w011",
          "p006-b001-r001-l007-w001",
          "p006-b001-r001-l007-w002",
          "p006-b001-r001-l007-w003",
          "p006-b001-r001-l007-w004",
          "p006-b001-r001-l007-w005",
          "p006-b001-r001-l007-w006",
          "p006-b001-r001-l007-w007",
          "p006-b001-r001-l007-w008",
          "p006-b001-r001-l007-w009",
          "p006-b001-r001-l008-w002",
          "p006-b001-r001-l008-w003",
          "p006-b001-r001-l008-w004",
          "p006-b001-r001-l008-w005",
          "p006-b001-r001-l008-w006",
          "p006-b001-r001-l008-w007",
          "p006-b001-r001-l008-w008",
          "p006-b001-r001-l008-w009",
          "p006-b001-r001-l008-w010",
          "p006-b001-r001-l008-w011",
          "p006-b001-r001-l008-w012",
          "p006-b001-r001-l008-w013",
          "p006-b001-r001-l008-w014",
          "p006-b001-r001-l009-w001",
          "p006-b001-r001-l009-w002",
          "p006-b001-r001-l009-w003",
          "p006-b001-r001-l009-w004",
          "p006-b001-r001-l009-w005",
          "p006-b001-r001-l009-w006",
          "p006-b001-r001-l009-w007",
          "p006-b001-r001-l009-w008",
          "p006-b001-r001-l009-w009",
          "p006-b001-r001-l009-w010",
          "p006-b001-r001-l009-w011",
          "p006-b001-r001-l010-w002",
          "p006-b001-r001-l010-w003",
          "p006-b001-r001-l010-w005",
          "p006-b001-r001-l010-w006",
          "p006-b001-r001-l010-w007",
          "p006-b001-r001-l010-w008",
          "p006-b001-r001-l010-w009",
          "p006-b001-r001-l010-w010",
          "p006-b001-r001-l010-w011",
          "p006-b001-r001-l010-w012",
          "p006-b002-r001-l001-w001",
          "p006-b002-r001-l001-w002",
          "p006-b002-r001-l001-w003",
          "p006-b002-r001-l001-w004",
          "p006-b002-r001-l001-w005",
          "p006-b002-r001-l001-w006",
          "p006-b002-r001-l001-w008",
          "p006-b002-r001-l001-w009",
          "p006-b002-r001-l001-w010",
          "p006-b002-r001-l001-w011",
          "p006-b002-r001-l002-w001"
        ],
        "bbox": {
          "x": 350,
          "y": 406,
          "width": 925,
          "height": 391
        },
        "matched_tokens": 114,
        "total_tokens": 117
      },
      "type": "diary_entry",
      "date": null,
      "place_source": null,
      "content": [
        {
          "id": "p006-b001-p001",
          "order": 1,
          "evidence": {
            "status": "not_attempted",
            "method": null,
            "ocr_word_ids": [],
            "bbox": null,
            "matched_tokens": 0,
            "total_tokens": 0
          },
          "type": "text",
          "role": "body",
          "lines": [
            {
              "line_number": 1,
              "segments": [
                {
                  "type": "text",
                  "text": "Thanks to our Heavenly Father.  The day was spent"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 2,
              "segments": [
                {
                  "type": "text",
                  "text": "pleasantly, by reading and conversation, and after"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 3,
              "segments": [
                {
                  "type": "text",
                  "text": "\"tea\" just before the song service I went in with Miss"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 4,
              "segments": [
                {
                  "type": "text",
                  "text": "Slater and had a nice talk with her sister who is very"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 5,
              "segments": [
                {
                  "type": "text",
                  "text": "ill - we had prayer and came out to the song service."
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 6,
              "segments": [
                {
                  "type": "text",
                  "text": "After which a little walk on deck, and down in the"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 7,
              "segments": [
                {
                  "type": "text",
                  "text": "saloon again while I am writing, Miss Holland is punch"
                }
              ],
              "line_end": "hyphen_word_break"
            },
            {
              "line_number": 8,
              "segments": [
                {
                  "type": "text",
                  "text": "ing my hand with a long pole.  I am at a table with a"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 9,
              "segments": [
                {
                  "type": "text",
                  "text": "lot of English men and women.  Now the steward says it"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 10,
              "segments": [
                {
                  "type": "text",
                  "text": "is eleven o'clock & shuts off the lights so I retire to"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 11,
              "segments": [
                {
                  "type": "text",
                  "text": "my state room and Mr. Morrison & myself eat an apple"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 12,
              "segments": [
                {
                  "type": "text",
                  "text": "each."
                }
              ],
              "line_end": "block_end"
            }
          ]
        }
      ]
    },
    {
      "id": "p006-b002",
      "order": 2,
      "continuation": {
        "from_previous": "no",
        "to_next": "no",
        "previous": null,
        "next": null
      },
      "evidence": {
        "status": "aligned",
        "method": "exact_normalized_token_sequence",
        "ocr_word_ids": [
          "p006-b003-r001-l001-w001",
          "p006-b003-r001-l001-w002",
          "p006-b003-r001-l001-w004",
          "p006-b003-r002-l001-w001",
          "p006-b003-r002-l001-w002",
          "p006-b003-r002-l001-w003",
          "p006-b003-r002-l001-w004",
          "p006-b003-r002-l001-w005",
          "p006-b003-r002-l001-w006",
          "p006-b003-r002-l001-w007",
          "p006-b003-r002-l002-w001",
          "p006-b003-r002-l002-w002",
          "p006-b003-r002-l002-w003",
          "p006-b003-r002-l002-w004",
          "p006-b003-r002-l002-w005",
          "p006-b003-r002-l002-w006",
          "p006-b003-r002-l002-w007",
          "p006-b003-r002-l002-w008",
          "p006-b003-r002-l003-w001",
          "p006-b003-r002-l003-w002",
          "p006-b003-r002-l003-w003",
          "p006-b003-r002-l003-w004",
          "p006-b003-r002-l003-w005",
          "p006-b003-r002-l003-w006",
          "p006-b003-r002-l003-w007",
          "p006-b003-r002-l003-w008",
          "p006-b003-r002-l004-w001",
          "p006-b003-r002-l004-w002",
          "p006-b003-r002-l004-w003",
          "p006-b003-r002-l004-w004",
          "p006-b003-r002-l004-w005",
          "p006-b003-r002-l004-w006",
          "p006-b003-r002-l004-w007",
          "p006-b003-r002-l004-w008",
          "p006-b003-r002-l004-w009",
          "p006-b003-r002-l005-w001",
          "p006-b003-r002-l005-w002",
          "p006-b003-r002-l005-w003",
          "p006-b003-r002-l005-w004",
          "p006-b003-r002-l005-w005",
          "p006-b003-r002-l005-w006",
          "p006-b003-r002-l005-w007",
          "p006-b003-r002-l005-w008",
          "p006-b003-r002-l005-w009",
          "p006-b003-r002-l005-w010",
          "p006-b003-r002-l005-w011",
          "p006-b003-r002-l006-w001",
          "p006-b003-r002-l006-w002",
          "p006-b003-r002-l006-w003",
          "p006-b003-r002-l006-w004",
          "p006-b003-r002-l006-w005",
          "p006-b003-r002-l006-w006",
          "p006-b003-r002-l006-w008",
          "p006-b003-r002-l006-w009",
          "p006-b003-r002-l006-w010",
          "p006-b003-r002-l006-w011",
          "p006-b003-r002-l006-w012",
          "p006-b003-r002-l006-w013",
          "p006-b003-r002-l007-w001",
          "p006-b003-r002-l007-w002",
          "p006-b003-r002-l007-w003",
          "p006-b003-r002-l007-w004",
          "p006-b003-r002-l007-w005",
          "p006-b003-r002-l007-w006",
          "p006-b003-r002-l007-w007",
          "p006-b003-r002-l007-w008",
          "p006-b003-r002-l007-w009",
          "p006-b003-r002-l008-w001",
          "p006-b003-r002-l008-w002",
          "p006-b003-r002-l008-w003",
          "p006-b003-r002-l008-w004",
          "p006-b003-r002-l008-w005",
          "p006-b003-r002-l008-w006",
          "p006-b003-r002-l008-w007",
          "p006-b003-r002-l008-w008",
          "p006-b003-r002-l009-w001",
          "p006-b003-r002-l009-w002"
        ],
        "bbox": {
          "x": 351,
          "y": 839,
          "width": 893,
          "height": 330
        },
        "matched_tokens": 77,
        "total_tokens": 77
      },
      "type": "diary_entry",
      "date": {
        "date_source": "Nov. 16 - Monday",
        "date_normalized": null,
        "normalization_status": "not_normalized",
        "normalization_confidence": null,
        "normalization_reason": null
      },
      "place_source": null,
      "content": [
        {
          "id": "p006-b002-p001",
          "order": 1,
          "evidence": {
            "status": "not_attempted",
            "method": null,
            "ocr_word_ids": [],
            "bbox": null,
            "matched_tokens": 0,
            "total_tokens": 0
          },
          "type": "text",
          "role": "dateline",
          "lines": [
            {
              "line_number": 1,
              "segments": [
                {
                  "type": "text",
                  "text": "Nov. 16 - Monday"
                }
              ],
              "line_end": "block_end"
            }
          ]
        },
        {
          "id": "p006-b002-p002",
          "order": 2,
          "evidence": {
            "status": "not_attempted",
            "method": null,
            "ocr_word_ids": [],
            "bbox": null,
            "matched_tokens": 0,
            "total_tokens": 0
          },
          "type": "text",
          "role": "body",
          "lines": [
            {
              "line_number": 1,
              "segments": [
                {
                  "type": "text",
                  "text": "Rather late about arising  great preparations about"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 2,
              "segments": [
                {
                  "type": "text",
                  "text": "getting ready to land.  Drawing in toward Ireland."
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 3,
              "segments": [
                {
                  "type": "text",
                  "text": "Nothing of importance happened except I became much"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 4,
              "segments": [
                {
                  "type": "text",
                  "text": "interested in Miss Jennie Holland, and we had several"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 5,
              "segments": [
                {
                  "type": "text",
                  "text": "nice walks together.  I told her how I liked her and"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 6,
              "segments": [
                {
                  "type": "text",
                  "text": "How I hated to leave her - we were out until after 12"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 7,
              "segments": [
                {
                  "type": "text",
                  "text": "midnight and then I Packed my trunk and telescope"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 8,
              "segments": [
                {
                  "type": "text",
                  "text": "preparatory to landing at Queenstown at 3 o'clock"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 9,
              "segments": [
                {
                  "type": "text",
                  "text": "Tuesday morning."
                }
              ],
              "line_end": "block_end"
            }
          ]
        }
      ]
    },
    {
      "id": "p006-b003",
      "order": 3,
      "continuation": {
        "from_previous": "no",
        "to_next": "yes",
        "previous": null,
        "next": null
      },
      "evidence": {
        "status": "partial",
        "method": "exact_normalized_token_sequence",
        "ocr_word_ids": [
          "p006-b004-r001-l001-w001",
          "p006-b004-r001-l001-w002",
          "p006-b004-r001-l001-w004",
          "p006-b004-r002-l001-w001",
          "p006-b004-r002-l001-w002",
          "p006-b004-r002-l001-w003",
          "p006-b004-r002-l001-w004",
          "p006-b004-r002-l001-w006",
          "p006-b004-r002-l001-w007",
          "p006-b004-r002-l001-w008",
          "p006-b004-r002-l001-w009",
          "p006-b004-r002-l001-w010",
          "p006-b004-r002-l001-w011",
          "p006-b004-r002-l002-w001",
          "p006-b004-r002-l002-w002",
          "p006-b004-r002-l002-w003",
          "p006-b004-r002-l002-w004",
          "p006-b004-r002-l002-w005",
          "p006-b004-r002-l002-w006",
          "p006-b004-r002-l002-w007",
          "p006-b004-r002-l002-w008",
          "p006-b004-r002-l002-w009",
          "p006-b004-r002-l002-w010",
          "p006-b004-r002-l002-w011",
          "p006-b004-r002-l002-w012",
          "p006-b004-r002-l003-w001",
          "p006-b004-r002-l003-w002",
          "p006-b004-r002-l003-w003",
          "p006-b004-r002-l003-w004",
          "p006-b004-r002-l003-w005",
          "p006-b004-r002-l003-w006",
          "p006-b004-r002-l003-w007",
          "p006-b004-r002-l003-w008",
          "p006-b004-r002-l003-w009",
          "p006-b004-r002-l003-w010",
          "p006-b004-r002-l003-w011",
          "p006-b004-r002-l004-w001",
          "p006-b004-r002-l004-w002",
          "p006-b004-r002-l004-w003",
          "p006-b004-r002-l004-w004",
          "p006-b004-r002-l004-w005",
          "p006-b004-r002-l004-w006",
          "p006-b004-r002-l004-w007",
          "p006-b004-r002-l004-w008",
          "p006-b004-r002-l004-w009",
          "p006-b004-r002-l004-w010",
          "p006-b004-r002-l004-w011",
          "p006-b004-r002-l004-w012",
          "p006-b004-r002-l005-w001",
          "p006-b004-r002-l005-w002",
          "p006-b004-r002-l005-w003",
          "p006-b004-r002-l005-w004",
          "p006-b004-r002-l005-w005",
          "p006-b004-r002-l005-w006",
          "p006-b004-r002-l005-w007",
          "p006-b004-r002-l005-w008",
          "p006-b004-r002-l005-w009",
          "p006-b004-r002-l006-w001",
          "p006-b004-r002-l006-w002",
          "p006-b004-r002-l006-w003",
          "p006-b004-r002-l006-w004",
          "p006-b004-r002-l006-w005",
          "p006-b004-r002-l006-w006",
          "p006-b004-r002-l006-w007",
          "p006-b004-r002-l006-w008",
          "p006-b004-r002-l006-w009",
          "p006-b004-r002-l006-w010",
          "p006-b004-r002-l007-w001",
          "p006-b004-r002-l007-w002",
          "p006-b004-r002-l007-w003",
          "p006-b004-r002-l007-w004",
          "p006-b004-r002-l007-w005",
          "p006-b004-r002-l007-w006",
          "p006-b004-r002-l007-w007",
          "p006-b004-r002-l007-w008",
          "p006-b004-r002-l007-w009",
          "p006-b004-r002-l007-w010",
          "p006-b004-r002-l007-w011",
          "p006-b004-r002-l008-w001",
          "p006-b004-r002-l008-w002",
          "p006-b004-r002-l008-w003",
          "p006-b004-r002-l008-w004",
          "p006-b004-r002-l008-w005",
          "p006-b004-r002-l008-w006",
          "p006-b004-r002-l008-w007",
          "p006-b004-r002-l008-w008",
          "p006-b004-r002-l008-w009",
          "p006-b004-r002-l009-w001",
          "p006-b004-r002-l009-w002",
          "p006-b004-r002-l009-w003",
          "p006-b004-r002-l009-w004",
          "p006-b004-r002-l009-w005",
          "p006-b004-r002-l009-w006",
          "p006-b004-r002-l009-w007",
          "p006-b004-r002-l009-w008",
          "p006-b004-r002-l009-w009",
          "p006-b004-r002-l010-w001",
          "p006-b004-r002-l010-w002",
          "p006-b004-r002-l010-w003",
          "p006-b004-r002-l010-w004",
          "p006-b004-r002-l010-w005",
          "p006-b004-r002-l010-w006",
          "p006-b004-r002-l010-w007",
          "p006-b004-r002-l010-w008",
          "p006-b004-r002-l010-w009",
          "p006-b004-r002-l010-w010",
          "p006-b004-r002-l010-w011",
          "p006-b004-r002-l011-w001",
          "p006-b004-r002-l011-w002",
          "p006-b004-r002-l011-w003",
          "p006-b004-r002-l011-w004",
          "p006-b004-r002-l011-w005",
          "p006-b004-r002-l011-w006",
          "p006-b004-r002-l011-w007",
          "p006-b004-r002-l011-w008",
          "p006-b004-r002-l011-w009",
          "p006-b004-r002-l012-w001",
          "p006-b004-r002-l012-w002",
          "p006-b004-r002-l012-w003",
          "p006-b004-r002-l012-w004",
          "p006-b004-r002-l012-w005",
          "p006-b004-r002-l012-w006",
          "p006-b004-r002-l012-w007",
          "p006-b004-r002-l012-w008",
          "p006-b004-r002-l012-w009",
          "p006-b004-r002-l012-w010",
          "p006-b004-r002-l013-w001",
          "p006-b004-r002-l013-w002",
          "p006-b004-r002-l013-w003",
          "p006-b004-r002-l013-w005",
          "p006-b004-r002-l013-w006",
          "p006-b004-r002-l013-w007",
          "p006-b004-r002-l013-w008",
          "p006-b004-r002-l013-w009",
          "p006-b004-r002-l014-w001",
          "p006-b004-r002-l014-w002",
          "p006-b004-r002-l014-w003",
          "p006-b004-r002-l014-w004",
          "p006-b004-r002-l014-w005",
          "p006-b004-r002-l014-w006",
          "p006-b004-r002-l014-w007",
          "p006-b004-r002-l014-w008",
          "p006-b004-r002-l014-w009",
          "p006-b004-r002-l015-w001",
          "p006-b004-r002-l015-w002",
          "p006-b004-r002-l015-w004",
          "p006-b004-r002-l015-w005",
          "p006-b004-r002-l015-w006",
          "p006-b004-r002-l015-w007",
          "p006-b004-r002-l015-w008",
          "p006-b004-r002-l015-w009",
          "p006-b004-r002-l015-w010",
          "p006-b004-r002-l015-w011",
          "p006-b004-r002-l015-w012",
          "p006-b004-r002-l016-w001",
          "p006-b004-r002-l016-w002",
          "p006-b004-r002-l016-w003",
          "p006-b004-r002-l016-w004",
          "p006-b004-r002-l016-w005",
          "p006-b004-r002-l016-w006",
          "p006-b004-r002-l016-w007",
          "p006-b004-r002-l016-w008",
          "p006-b004-r002-l016-w009",
          "p006-b004-r002-l017-w001",
          "p006-b004-r002-l017-w002",
          "p006-b004-r002-l017-w004",
          "p006-b004-r002-l017-w005",
          "p006-b004-r002-l017-w006",
          "p006-b004-r002-l017-w007",
          "p006-b004-r002-l017-w008",
          "p006-b004-r002-l017-w009",
          "p006-b004-r002-l017-w010",
          "p006-b004-r002-l018-w001",
          "p006-b004-r002-l018-w002",
          "p006-b004-r002-l018-w003",
          "p006-b004-r002-l018-w004",
          "p006-b004-r002-l018-w005",
          "p006-b004-r002-l018-w006",
          "p006-b004-r002-l018-w007",
          "p006-b004-r002-l018-w008",
          "p006-b004-r002-l018-w009",
          "p006-b004-r002-l018-w010",
          "p006-b004-r002-l018-w011",
          "p006-b004-r002-l019-w001",
          "p006-b004-r002-l019-w002",
          "p006-b004-r002-l019-w003",
          "p006-b004-r002-l019-w004",
          "p006-b004-r002-l019-w005",
          "p006-b004-r002-l019-w006",
          "p006-b004-r002-l019-w007",
          "p006-b004-r002-l019-w008",
          "p006-b004-r002-l019-w009",
          "p006-b004-r002-l019-w010",
          "p006-b004-r002-l019-w011",
          "p006-b004-r002-l020-w001",
          "p006-b004-r002-l020-w002",
          "p006-b004-r002-l020-w003",
          "p006-b004-r002-l020-w004",
          "p006-b004-r002-l020-w005",
          "p006-b004-r002-l020-w006",
          "p006-b004-r002-l020-w007",
          "p006-b004-r002-l020-w008"
        ],
        "bbox": {
          "x": 353,
          "y": 1206,
          "width": 875,
          "height": 695
        },
        "matched_tokens": 203,
        "total_tokens": 207
      },
      "type": "diary_entry",
      "date": {
        "date_source": "Nov. 17 - Tuesday",
        "date_normalized": null,
        "normalization_status": "not_normalized",
        "normalization_confidence": null,
        "normalization_reason": null
      },
      "place_source": null,
      "content": [
        {
          "id": "p006-b003-p001",
          "order": 1,
          "evidence": {
            "status": "not_attempted",
            "method": null,
            "ocr_word_ids": [],
            "bbox": null,
            "matched_tokens": 0,
            "total_tokens": 0
          },
          "type": "text",
          "role": "dateline",
          "lines": [
            {
              "line_number": 1,
              "segments": [
                {
                  "type": "text",
                  "text": "Nov. 17 - Tuesday"
                }
              ],
              "line_end": "block_end"
            }
          ]
        },
        {
          "id": "p006-b003-p002",
          "order": 2,
          "evidence": {
            "status": "not_attempted",
            "method": null,
            "ocr_word_ids": [],
            "bbox": null,
            "matched_tokens": 0,
            "total_tokens": 0
          },
          "type": "text",
          "role": "body",
          "lines": [
            {
              "line_number": 1,
              "segments": [
                {
                  "type": "text",
                  "text": "At 4 o'clock this a.m. the steward called me to get"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 2,
              "segments": [
                {
                  "type": "text",
                  "text": "up and have some coffee as we were soon to stop at"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 3,
              "segments": [
                {
                  "type": "text",
                  "text": "Queenstown.  I got up and nearly all on board got up"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 4,
              "segments": [
                {
                  "type": "text",
                  "text": "to see those off who were going to land at Q.  But"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 5,
              "segments": [
                {
                  "type": "text",
                  "text": "something was wrong at the signal stations and the"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 6,
              "segments": [
                {
                  "type": "text",
                  "text": "tender (the boat on which we were unloaded) did not"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 7,
              "segments": [
                {
                  "type": "text",
                  "text": "get the news of our arrival so we anchored about 2"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 8,
              "segments": [
                {
                  "type": "text",
                  "text": "hours.  Miss H and myself had a nice-pleasant time"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 9,
              "segments": [
                {
                  "type": "text",
                  "text": "walking and talking until the tender came.  I then"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 10,
              "segments": [
                {
                  "type": "text",
                  "text": "got on the tender and went up the Cork Harbor to"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 11,
              "segments": [
                {
                  "type": "text",
                  "text": "Queenstown about an hour's ride.  The water in the"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 12,
              "segments": [
                {
                  "type": "text",
                  "text": "harbor was very placid and as it was just getting"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 13,
              "segments": [
                {
                  "type": "text",
                  "text": "light the hills & garrisons on either side looked"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 14,
              "segments": [
                {
                  "type": "text",
                  "text": "beautiful.  The scenery is grand.  We arrived at Q."
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 15,
              "segments": [
                {
                  "type": "text",
                  "text": "at 7 a.m. I together with a lot of others, and went"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 16,
              "segments": [
                {
                  "type": "text",
                  "text": "into the Custom House and had our packages opened"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 17,
              "segments": [
                {
                  "type": "text",
                  "text": "and inspected - no goods which were subject to duty,"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 18,
              "segments": [
                {
                  "type": "text",
                  "text": "except a box of cigars which I was careful to take"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 19,
              "segments": [
                {
                  "type": "text",
                  "text": "out of the box and put in my overcoat pocket.  I"
                }
              ],
              "line_end": "no_hyphen"
            },
            {
              "line_number": 20,
              "segments": [
                {
                  "type": "text",
                  "text": "then went uptown with Mrs. Abraham, the Garrigan"
                }
              ],
              "line_end": "no_hyphen"
            }
          ]
        }
      ]
    }
  ],
  "editorial_notes": [],
  "provenance": {
    "pipeline_version": "0.1.0",
    "model_run_id": "20260808T180301Z-eval",
    "backend": "codex-exec",
    "model": "gpt-5.6-sol",
    "reasoning_effort": "xhigh",
    "prompt_sha256": "eebd92ab915971f497854ea2d36d9fc8ca91724afad55242695e4ad5d80e966a",
    "schema_sha256": "a1c29dca3f75ac07c6939242f315bb53cac9c82f75ce42df8aa1c4721bf9f056",
    "candidate_sha256": "ba4e0b14400a625d040404afba5ce910c7ea781de286ad935075d542ce31585f",
    "context_pages": [
      5,
      7
    ],
    "steps": [
      {
        "kind": "ocr",
        "actor": "tesseract 5.5.0",
        "artifact": "ocr/page-006.txt",
        "created_at": "2026-08-08T18:03:49Z"
      },
      {
        "kind": "model_transcription",
        "actor": "codex-exec:gpt-5.6-sol",
        "artifact": "20260808T180301Z-eval",
        "created_at": "2026-08-08T18:03:49Z"
      },
      {
        "kind": "agent_review",
        "actor": "Codex",
        "artifact": "artifacts/runs/20260808T180301Z-eval/candidates/page-006.json",
        "created_at": "2026-08-08T18:09:26Z"
      },
      {
        "kind": "owner_review",
        "actor": "John Crowley",
        "artifact": "evaluation/goldens/page-006.json",
        "created_at": "2026-08-08T20:02:47Z",
        "action": "approve_as_is",
        "input_sha256": "77fc639f18af7b5f576a7ef0eb3fd30008107b36a3c5fa0bbe66df168ed44b02",
        "change_categories": []
      }
    ]
  },
  "review": {
    "status": "owner_approved",
    "authority": "owner_approved_edition",
    "reviewer": "John Crowley",
    "reviewed_at": "2026-08-08T20:02:47Z",
    "notes": [
      "Diagnostic fixture only; it is not independent ground truth and has not been owner-approved.",
      "Compared the complete page transcription with the authoritative page image.",
      "Corrected the visibly intentional source hyphen in nice-pleasant; the model had silently omitted it.",
      "Explicit owner action: approve_as_is.",
      "Approval lineage begins with diagnostic SHA-256 77fc639f18af7b5f576a7ef0eb3fd30008107b36a3c5fa0bbe66df168ed44b02.",
      "Owner visually compared the diagnostic with the authoritative scan and approved it without further changes."
    ]
  }
}