Authoritative page image
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
- The first nine visible lines form a fully cancelled draft entry; an uncancelled entry for the same date follows.
- Diagnostic fixture only; it is not independent ground truth and has not been owner-approved.
- Compared the fully cancelled top passage and the retyped Friday-through-Monday entries against the authoritative page image.
- No text changes were required. The diagnostic retains the cancelled top region as one draft diary block even though a struck Saturday heading occurs inside it; this is a documented schema/segmentation ambiguity.
- Explicit owner action: approve_as_is.
- Approval lineage begins with diagnostic SHA-256 686ee1ebe1fbe83e934fef1ed9f76c74d25989cfd980e0211648d759120dcd65.
- Owner visually compared the diagnostic with the authoritative scan and approved it without further changes.
Current edition reading text
- Friday Oct. 20 - 99 Sophie went to Kinshasa in hammock - I went to Ndele on train took my bike - saw the new bot of CCC Mr. Loyd is Chief builder - I then came to Gordons & had dinner. Afterwards I went to Dutch House, about 4 o'clock S.S.. Reed came in (A.B.M.U.) & Gordon & I went to the custom house to meet it, Mr. Banks master. Mrs. Crowley & I then came down to Leo. with him. He will stay with us until Monday when he will leave for Hout Congo. Mr. Black has decided to go up with him Leopoldville Saturday Oct. 21 - 99 This a.m. I got out loads for A.B.M.U. & C.B.M. & had them put on the beach I made out a list &c & sent to the Custom Officer & had the Extait du Permis signed a very busy day - packages large & steamer small - Difficult to load. Sunday Oct. 22 - 99 Service this a.m. was good - large attendance. Nkaku Interpreted what I preached to them. Mrs. Crowley's service in the p.m. was very largely attended. My service in English was nothing. Prayers for & with the boys & then to bed. Monday Oct. 23 - 99 Mr. Banks called me early & I had to add a few more loads to the list - About 9 o'clock the steamer left - we sent a piece of ham & some bread & cakes with Mr. Banks Mr. Black gone with him as a passenger. He is strictly a vegetarian - I don't know how he will get on. Sophie not well so I could not go over to Kinshasa on boat. I nearly always go over when a boat leaves. In that way I keep up with what goes on all around & it saves me a trip on my wheel or on train one way.
Current edition diplomatic rendering
⟦deleted: Friday Oct. 20 - 99 "Roi de Belge"⟧ ⟦deleted: Steamer left - "Ville-deBruges" - this a.m. for Kassai⟧- ⟦deleted: has only charges - hope she will get there o.k. - Sophie⟧ ⟦deleted: not very well - so did not go to Kinshasa - C.B.M. had⟧ ⟦deleted: 70 loads come in & my boys with theirs had them down by⟧ ⟦deleted: noon. About it rained a little - Black makes mistakes⟧ ⟦deleted: Today Sophie went to Kinshasa in hammock - I went to⟧ ⟦deleted: Saturday Oct. 21 - 1899 Ndele on train took my bike &⟧ ⟦deleted: came back on her - Ate dinner with Gordon & Wife -⟧ Friday Oct. 20 - 99 Sophie went to Kinshasa in hammock - I went to Ndele on train took my bike - saw the new bot of CCC Mr. Loyd is Chief builder - I then came to Gordons & had dinner. Afterwards I went to Dutch House, about 4 o'clock S.S.. Reed came in (A.B.M.U.) & Gordon & I went to the custom house to meet it, Mr. Banks master. Mrs. Crowley & I then came down to Leo. with him. He will stay with us until Monday when he will leave for Hout Congo. Mr. Black has decided to go up with him Leopoldville Saturday Oct. 21 - 99 This a.m. I got out loads for A.B.M.U. & C.B.M. & had them put on the beach I made out a list &c & sent to the Custom Officer & had the Extait du Permis signed a very busy day - packages large & steamer small - Diffi- cult to load. Sunday Oct. 22 - 99 Service this a.m. was good - large attendance. Nkaku Interpreted what I preached to them. Mrs. Crowley's service in the p.m. was very largely attended. My service in English was nothing. Prayers for & with the boys & then to bed. Monday Oct. 23 - 99 Mr. Banks called me early & I had to add a few more loads to the list - About 9 o'clock the steamer left - we sent a piece of ham & some bread & cakes with Mr. Banks Mr. Black gone with him as a passenger. He is strictly a vegetarian - I don't know how he will get on. Sophie not well so I could not go over to Kinshasa on boat. I nearly always go over when a boat leaves. In that way I keep up with what goes on all around & it saves me a trip on my wheel or on train one way.
Raw OCR
em down by makes mistakes Friday Oct. 20 - 99 Sephie went te Kinshasa in hammeck ~ I went te Ndele on train teek my bike - saw the new bet of CCC Mr. Leyd is Chief builder ~ I then came te Gerdons & had dinner. Afterwards I went te Dutch House, about 4 e'cleck 8.S.. Reed came in (A.B.M.U.) & Gorden & I went te the custem house te meet it, Mr. Banks master. Mrs. Crewley & I then came dewn te Lee. with him. He will stay with us until Monday when he will leave for Hout Cenge. Mr. Black has decided te ge up with him Leopeldville Saturday Oct. 21 = 99 This aem. I got out leads for A.B.M.U. & C.BM. & had them put en the beach I made eut a list &e & sent te the Custem Officer & had the Extait du Permis signed @ very busy day - packages large & steamer small - Diffi-~ sult te load. Sunday Oct. 22 - 99 Service this a-m. was goed - large attendance. Nkaku Interpreted what I preached to then. Mrs. Crewley's service in the p.m. was very largely attended. My service in English was nething. Prayers fer & with the boys & then te bed. Monday Oct. 23 - 99 Mr. Banks called me early & I had to add a few more leads te the list - About 9 e'clock the steamer left - we sent a piece of ham & some bread & cakes with Mr. Banks Mr. Black gone with him as a passenger. He is strictly a vegetarian - I doen't know how he will get on. Sophie net well so I could net go ever to Kinshasa en beat. I nearly always go over when a beat leaves. In that way I keep up with what gees on all around & it saves me a trip en my wheel er on train one way.
Candidate-to-diagnostic reading diff
No reading-text difference.
Candidate-to-diagnostic canonical JSON diff
Categories: review metadata only
--- model-candidate
+++ agent-diagnostic
@@ -1,5 +1,5 @@
{
- "schema_version": "1.0.0",
+ "schema_version": "1.1.0",
"page_id": "page-289",
"source": {
"pdf_page": 289,
@@ -1083,16 +1083,24 @@
"actor": "codex-exec:gpt-5.6-sol",
"artifact": "20260808T180301Z-eval",
"created_at": "2026-08-08T18:37:07Z"
+ },
+ {
+ "kind": "agent_review",
+ "actor": "Codex",
+ "artifact": "artifacts/runs/20260808T180301Z-eval/candidates/page-289.json",
+ "created_at": "2026-08-08T18:38:26Z"
}
]
},
"review": {
- "status": "model_candidate",
+ "status": "agent_reviewed",
"authority": "diagnostic_only",
- "reviewer": null,
- "reviewed_at": null,
+ "reviewer": "Codex",
+ "reviewed_at": "2026-08-08T18:38:26Z",
"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 fully cancelled top passage and the retyped Friday-through-Monday entries against the authoritative page image.",
+ "No text changes were required. The diagnostic retains the cancelled top region as one draft diary block even though a struck Saturday heading occurs inside it; this is a documented schema/segmentation ambiguity."
]
}
}
Diagnostic-to-owner reading diff
No reading-text difference.
Diagnostic-to-owner canonical JSON diff
--- agent-diagnostic
+++ owner-approved-edition
@@ -1089,18 +1089,30 @@
"actor": "Codex",
"artifact": "artifacts/runs/20260808T180301Z-eval/candidates/page-289.json",
"created_at": "2026-08-08T18:38:26Z"
+ },
+ {
+ "kind": "owner_review",
+ "actor": "John Crowley",
+ "artifact": "evaluation/goldens/page-289.json",
+ "created_at": "2026-08-08T20:02:49Z",
+ "action": "approve_as_is",
+ "input_sha256": "686ee1ebe1fbe83e934fef1ed9f76c74d25989cfd980e0211648d759120dcd65",
+ "change_categories": []
}
]
},
"review": {
- "status": "agent_reviewed",
- "authority": "diagnostic_only",
- "reviewer": "Codex",
- "reviewed_at": "2026-08-08T18:38:26Z",
+ "status": "owner_approved",
+ "authority": "owner_approved_edition",
+ "reviewer": "John Crowley",
+ "reviewed_at": "2026-08-08T20:02:49Z",
"notes": [
"Diagnostic fixture only; it is not independent ground truth and has not been owner-approved.",
"Compared the fully cancelled top passage and the retyped Friday-through-Monday entries against the authoritative page image.",
- "No text changes were required. The diagnostic retains the cancelled top region as one draft diary block even though a struck Saturday heading occurs inside it; this is a documented schema/segmentation ambiguity."
+ "No text changes were required. The diagnostic retains the cancelled top region as one draft diary block even though a struck Saturday heading occurs inside it; this is a documented schema/segmentation ambiguity.",
+ "Explicit owner action: approve_as_is.",
+ "Approval lineage begins with diagnostic SHA-256 686ee1ebe1fbe83e934fef1ed9f76c74d25989cfd980e0211648d759120dcd65.",
+ "Owner visually compared the diagnostic with the authoritative scan and approved it without further changes."
]
}
}
Raw model candidate JSON
{
"schema_version": "1.0.0",
"page_id": "page-289",
"source": {
"pdf_page": 289,
"source_pdf_sha256": "80a074ed94fded84fa8a455d61fbf94b25cd4f1239d5ec3e639aaf443467c53f",
"image": {
"path": "pages/page-289.png",
"sha256": "6f943b49e061c8e90fde45fb27a6db8fd596955789e62e7eb307a1afab883569",
"width": 1700,
"height": 2200,
"dpi": 200
},
"ocr": {
"text_path": "ocr/page-289.txt",
"text_sha256": "ee18497cd562b77ce39e497b854923fc2584f74bce016ae16453ebf194cbfa22",
"tsv_path": "ocr/page-289.tsv",
"tsv_sha256": "38a1662b58ba938f5dbf5bf3776d2943bf1c8f591c019e00481a4d7b878e8a40",
"engine": "tesseract 5.5.0"
}
},
"segment": {
"id": "book-05",
"kind": "book",
"label_source": "Last book",
"assignment_status": "inferred"
},
"page_role": "content",
"boundary": {
"starts_mid_block": "no",
"ends_mid_block": "no"
},
"blocks": [
{
"id": "p289-b001",
"order": 1,
"continuation": {
"from_previous": "no",
"to_next": "no",
"previous": null,
"next": null
},
"evidence": {
"status": "unaligned",
"method": null,
"ocr_word_ids": [],
"bbox": null,
"matched_tokens": 0,
"total_tokens": 0
},
"type": "diary_entry",
"date": {
"date_source": "Friday Oct. 20 - 99",
"date_normalized": "1899-10-20",
"normalization_status": "normalized",
"normalization_confidence": "high",
"normalization_reason": "Expanded the two-digit year and converted the date to ISO format."
},
"place_source": null,
"content": [
{
"id": "p289-b001-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": "deletion",
"medium": "handwritten",
"method": "cancelled",
"reading": "Friday Oct. 20 - 99 \"Roi de Belge\"",
"alternatives": [],
"confidence": "high"
}
],
"line_end": "block_end"
}
]
},
{
"id": "p289-b001-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": "deletion",
"medium": "handwritten",
"method": "cancelled",
"reading": "Steamer left - \"Ville-deBruges\" - this a.m. for Kassai",
"alternatives": [],
"confidence": "medium"
}
],
"line_end": "hyphen_lexical"
},
{
"line_number": 2,
"segments": [
{
"type": "deletion",
"medium": "handwritten",
"method": "cancelled",
"reading": "has only charges - hope she will get there o.k. - Sophie",
"alternatives": [],
"confidence": "high"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 3,
"segments": [
{
"type": "deletion",
"medium": "handwritten",
"method": "cancelled",
"reading": "not very well - so did not go to Kinshasa - C.B.M. had",
"alternatives": [],
"confidence": "high"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 4,
"segments": [
{
"type": "deletion",
"medium": "handwritten",
"method": "cancelled",
"reading": "70 loads come in & my boys with theirs had them down by",
"alternatives": [],
"confidence": "high"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 5,
"segments": [
{
"type": "deletion",
"medium": "handwritten",
"method": "cancelled",
"reading": "noon. About it rained a little - Black makes mistakes",
"alternatives": [],
"confidence": "medium"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 6,
"segments": [
{
"type": "deletion",
"medium": "handwritten",
"method": "cancelled",
"reading": "Today Sophie went to Kinshasa in hammock - I went to",
"alternatives": [],
"confidence": "high"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 7,
"segments": [
{
"type": "deletion",
"medium": "handwritten",
"method": "cancelled",
"reading": "Saturday Oct. 21 - 1899 Ndele on train took my bike &",
"alternatives": [],
"confidence": "medium"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 8,
"segments": [
{
"type": "deletion",
"medium": "handwritten",
"method": "cancelled",
"reading": "came back on her - Ate dinner with Gordon & Wife -",
"alternatives": [],
"confidence": "high"
}
],
"line_end": "block_end"
}
]
}
]
},
{
"id": "p289-b002",
"order": 2,
"continuation": {
"from_previous": "no",
"to_next": "no",
"previous": null,
"next": null
},
"evidence": {
"status": "partial",
"method": "exact_normalized_token_sequence",
"ocr_word_ids": [
"p289-b003-r001-l001-w001",
"p289-b003-r001-l001-w002",
"p289-b003-r001-l001-w003",
"p289-b003-r001-l001-w005",
"p289-b003-r001-l002-w002",
"p289-b003-r001-l002-w004",
"p289-b003-r001-l002-w005",
"p289-b003-r001-l002-w008",
"p289-b003-r001-l002-w009",
"p289-b003-r001-l002-w011",
"p289-b003-r001-l002-w012",
"p289-b003-r001-l003-w001",
"p289-b003-r001-l003-w003",
"p289-b003-r001-l003-w004",
"p289-b003-r001-l003-w006",
"p289-b003-r001-l003-w007",
"p289-b003-r001-l003-w008",
"p289-b003-r001-l003-w010",
"p289-b003-r001-l003-w011",
"p289-b003-r001-l003-w012",
"p289-b003-r001-l004-w001",
"p289-b003-r001-l004-w002",
"p289-b003-r001-l004-w003",
"p289-b003-r001-l004-w005",
"p289-b003-r001-l004-w006",
"p289-b003-r001-l004-w007",
"p289-b003-r001-l004-w011",
"p289-b003-r001-l004-w012",
"p289-b003-r001-l005-w001",
"p289-b003-r001-l005-w002",
"p289-b003-r001-l005-w003",
"p289-b003-r001-l005-w005",
"p289-b003-r001-l005-w006",
"p289-b003-r001-l005-w007",
"p289-b003-r001-l005-w008",
"p289-b003-r001-l005-w010",
"p289-b003-r001-l006-w001",
"p289-b003-r001-l006-w002",
"p289-b003-r001-l006-w003",
"p289-b003-r001-l006-w004",
"p289-b003-r001-l006-w008",
"p289-b003-r001-l006-w009",
"p289-b003-r001-l006-w011",
"p289-b003-r001-l007-w001",
"p289-b003-r001-l007-w003",
"p289-b003-r001-l007-w004",
"p289-b003-r001-l007-w005",
"p289-b003-r001-l007-w006",
"p289-b003-r001-l007-w007",
"p289-b003-r001-l007-w008",
"p289-b003-r001-l007-w011",
"p289-b003-r001-l008-w001",
"p289-b003-r001-l008-w002",
"p289-b003-r001-l008-w006",
"p289-b003-r001-l008-w007",
"p289-b003-r001-l008-w008",
"p289-b003-r001-l008-w009",
"p289-b003-r001-l008-w010",
"p289-b003-r001-l008-w011",
"p289-b003-r001-l008-w012",
"p289-b003-r001-l009-w001",
"p289-b003-r001-l009-w002",
"p289-b003-r001-l009-w003",
"p289-b003-r001-l009-w004",
"p289-b003-r001-l009-w005",
"p289-b003-r001-l009-w006",
"p289-b003-r001-l009-w007",
"p289-b003-r001-l009-w008",
"p289-b003-r001-l009-w010",
"p289-b003-r001-l010-w001",
"p289-b003-r001-l010-w002",
"p289-b003-r001-l010-w003",
"p289-b003-r001-l010-w006",
"p289-b003-r001-l010-w007",
"p289-b003-r001-l010-w008"
],
"bbox": {
"x": 371,
"y": 740,
"width": 924,
"height": 328
},
"matched_tokens": 78,
"total_tokens": 101
},
"type": "diary_entry",
"date": {
"date_source": "Friday Oct. 20 - 99",
"date_normalized": "1899-10-20",
"normalization_status": "normalized",
"normalization_confidence": "high",
"normalization_reason": "Expanded the two-digit year and converted the date to ISO format."
},
"place_source": null,
"content": [
{
"id": "p289-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": "Friday Oct. 20 - 99"
}
],
"line_end": "block_end"
}
]
},
{
"id": "p289-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": "Sophie went to Kinshasa in hammock - I went to Ndele on"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 2,
"segments": [
{
"type": "text",
"text": "train took my bike - saw the new bot of CCC Mr. Loyd"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 3,
"segments": [
{
"type": "text",
"text": "is Chief builder - I then came to Gordons & had dinner."
}
],
"line_end": "no_hyphen"
},
{
"line_number": 4,
"segments": [
{
"type": "text",
"text": "Afterwards I went to Dutch House, about 4 o'clock S.S.."
}
],
"line_end": "no_hyphen"
},
{
"line_number": 5,
"segments": [
{
"type": "text",
"text": "Reed came in (A.B.M.U.) & Gordon & I went to the custom"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 6,
"segments": [
{
"type": "text",
"text": "house to meet it, Mr. Banks master. Mrs. Crowley & I"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 7,
"segments": [
{
"type": "text",
"text": "then came down to Leo. with him. He will stay with us"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 8,
"segments": [
{
"type": "text",
"text": "until Monday when he will leave for Hout Congo. Mr."
}
],
"line_end": "no_hyphen"
},
{
"line_number": 9,
"segments": [
{
"type": "text",
"text": "Black has decided to go up with him"
}
],
"line_end": "block_end"
}
]
}
]
},
{
"id": "p289-b003",
"order": 3,
"continuation": {
"from_previous": "no",
"to_next": "no",
"previous": null,
"next": null
},
"evidence": {
"status": "partial",
"method": "exact_normalized_token_sequence",
"ocr_word_ids": [
"p289-b004-r001-l001-w002",
"p289-b004-r001-l001-w003",
"p289-b004-r001-l001-w004",
"p289-b004-r001-l001-w006",
"p289-b004-r002-l001-w001",
"p289-b004-r002-l001-w003",
"p289-b004-r002-l001-w004",
"p289-b004-r002-l001-w005",
"p289-b004-r002-l001-w007",
"p289-b004-r002-l001-w008",
"p289-b004-r002-l001-w010",
"p289-b004-r002-l001-w012",
"p289-b004-r002-l002-w001",
"p289-b004-r002-l002-w002",
"p289-b004-r002-l002-w004",
"p289-b004-r002-l002-w005",
"p289-b004-r002-l002-w006",
"p289-b004-r002-l002-w007",
"p289-b004-r002-l002-w009",
"p289-b004-r002-l002-w010",
"p289-b004-r002-l002-w013",
"p289-b004-r002-l003-w001",
"p289-b004-r002-l003-w003",
"p289-b004-r002-l003-w005",
"p289-b004-r002-l003-w006",
"p289-b004-r002-l003-w007",
"p289-b004-r002-l003-w008",
"p289-b004-r002-l003-w009",
"p289-b004-r002-l003-w010",
"p289-b005-r001-l001-w002",
"p289-b005-r001-l001-w003",
"p289-b005-r001-l001-w004",
"p289-b005-r001-l001-w006",
"p289-b005-r001-l001-w007",
"p289-b005-r001-l001-w009",
"p289-b005-r001-l001-w010",
"p289-b005-r001-l002-w003"
],
"bbox": {
"x": 374,
"y": 1105,
"width": 887,
"height": 184
},
"matched_tokens": 40,
"total_tokens": 54
},
"type": "diary_entry",
"date": {
"date_source": "Saturday Oct. 21 - 99",
"date_normalized": "1899-10-21",
"normalization_status": "normalized",
"normalization_confidence": "high",
"normalization_reason": "Expanded the two-digit year and converted the date to ISO format."
},
"place_source": "Leopoldville",
"content": [
{
"id": "p289-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": "Leopoldville Saturday Oct. 21 - 99"
}
],
"line_end": "block_end"
}
]
},
{
"id": "p289-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": "This a.m. I got out loads for A.B.M.U. & C.B.M. & had"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 2,
"segments": [
{
"type": "text",
"text": "them put on the beach I made out a list &c & sent to"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 3,
"segments": [
{
"type": "text",
"text": "the Custom Officer & had the Extait du Permis signed"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 4,
"segments": [
{
"type": "text",
"text": "a very busy day - packages large & steamer small - Diffi"
}
],
"line_end": "hyphen_word_break"
},
{
"line_number": 5,
"segments": [
{
"type": "text",
"text": "cult to load."
}
],
"line_end": "block_end"
}
]
}
]
},
{
"id": "p289-b004",
"order": 4,
"continuation": {
"from_previous": "no",
"to_next": "no",
"previous": null,
"next": null
},
"evidence": {
"status": "partial",
"method": "exact_normalized_token_sequence",
"ocr_word_ids": [
"p289-b006-r001-l001-w001",
"p289-b006-r001-l001-w002",
"p289-b006-r001-l001-w003",
"p289-b006-r001-l001-w005",
"p289-b006-r002-l001-w001",
"p289-b006-r002-l001-w002",
"p289-b006-r002-l001-w003",
"p289-b006-r002-l001-w004",
"p289-b006-r002-l001-w007",
"p289-b006-r002-l001-w008",
"p289-b006-r002-l001-w009",
"p289-b006-r002-l002-w001",
"p289-b006-r002-l002-w002",
"p289-b006-r002-l002-w003",
"p289-b006-r002-l002-w004",
"p289-b006-r002-l002-w005",
"p289-b006-r002-l002-w007",
"p289-b006-r002-l003-w001",
"p289-b006-r002-l003-w002",
"p289-b006-r002-l003-w003",
"p289-b006-r002-l003-w004",
"p289-b006-r002-l003-w005",
"p289-b006-r002-l003-w006",
"p289-b006-r002-l003-w007",
"p289-b006-r002-l003-w008",
"p289-b006-r002-l003-w009",
"p289-b006-r002-l004-w001",
"p289-b006-r002-l004-w002",
"p289-b006-r002-l004-w003",
"p289-b006-r002-l004-w004",
"p289-b006-r002-l004-w006",
"p289-b006-r002-l004-w009",
"p289-b006-r002-l004-w010",
"p289-b006-r002-l005-w001",
"p289-b006-r002-l005-w003",
"p289-b006-r002-l005-w005"
],
"bbox": {
"x": 374,
"y": 1334,
"width": 920,
"height": 192
},
"matched_tokens": 38,
"total_tokens": 44
},
"type": "diary_entry",
"date": {
"date_source": "Sunday Oct. 22 - 99",
"date_normalized": "1899-10-22",
"normalization_status": "normalized",
"normalization_confidence": "high",
"normalization_reason": "Expanded the two-digit year and converted the date to ISO format."
},
"place_source": null,
"content": [
{
"id": "p289-b004-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": "Sunday Oct. 22 - 99"
}
],
"line_end": "block_end"
}
]
},
{
"id": "p289-b004-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": "Service this a.m. was good - large attendance. Nkaku"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 2,
"segments": [
{
"type": "text",
"text": "Interpreted what I preached to them. Mrs. Crowley's"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 3,
"segments": [
{
"type": "text",
"text": "service in the p.m. was very largely attended. My"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 4,
"segments": [
{
"type": "text",
"text": "service in English was nothing. Prayers for & with the"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 5,
"segments": [
{
"type": "text",
"text": "boys & then to bed."
}
],
"line_end": "block_end"
}
]
}
]
},
{
"id": "p289-b005",
"order": 5,
"continuation": {
"from_previous": "no",
"to_next": "no",
"previous": null,
"next": null
},
"evidence": {
"status": "partial",
"method": "exact_normalized_token_sequence",
"ocr_word_ids": [
"p289-b007-r001-l001-w001",
"p289-b007-r001-l001-w002",
"p289-b007-r001-l001-w003",
"p289-b007-r001-l001-w005",
"p289-b007-r002-l001-w001",
"p289-b007-r002-l001-w002",
"p289-b007-r002-l001-w003",
"p289-b007-r002-l001-w004",
"p289-b007-r002-l001-w005",
"p289-b007-r002-l001-w007",
"p289-b007-r002-l001-w008",
"p289-b007-r002-l001-w009",
"p289-b007-r002-l001-w010",
"p289-b007-r002-l001-w011",
"p289-b007-r002-l001-w012",
"p289-b007-r002-l001-w013",
"p289-b007-r002-l002-w002",
"p289-b007-r002-l002-w003",
"p289-b007-r002-l002-w005",
"p289-b007-r002-l002-w006",
"p289-b007-r002-l002-w008",
"p289-b007-r002-l002-w009",
"p289-b007-r002-l002-w010",
"p289-b007-r002-l002-w012",
"p289-b007-r002-l002-w013",
"p289-b007-r002-l003-w001",
"p289-b007-r002-l003-w002",
"p289-b007-r002-l003-w003",
"p289-b007-r002-l003-w004",
"p289-b007-r002-l003-w006",
"p289-b007-r002-l003-w007",
"p289-b007-r002-l003-w009",
"p289-b007-r002-l003-w010",
"p289-b007-r002-l003-w011",
"p289-b007-r002-l003-w012",
"p289-b007-r003-l001-w001",
"p289-b007-r003-l001-w002",
"p289-b007-r003-l001-w003",
"p289-b007-r003-l001-w004",
"p289-b007-r003-l001-w005",
"p289-b007-r003-l001-w006",
"p289-b007-r003-l001-w007",
"p289-b007-r003-l001-w008",
"p289-b007-r003-l001-w009",
"p289-b007-r003-l001-w010",
"p289-b007-r003-l001-w011",
"p289-b007-r003-l002-w001",
"p289-b007-r003-l002-w002",
"p289-b007-r003-l002-w004",
"p289-b007-r003-l002-w006",
"p289-b007-r003-l002-w007",
"p289-b007-r003-l002-w008",
"p289-b007-r003-l002-w009",
"p289-b007-r003-l002-w010",
"p289-b007-r003-l002-w011",
"p289-b007-r003-l002-w012",
"p289-b007-r003-l003-w002",
"p289-b007-r003-l003-w003",
"p289-b007-r003-l003-w004",
"p289-b007-r003-l003-w005",
"p289-b007-r003-l003-w007",
"p289-b007-r003-l003-w009",
"p289-b007-r003-l003-w010",
"p289-b007-r003-l003-w013",
"p289-b007-r003-l004-w001",
"p289-b007-r003-l004-w002",
"p289-b007-r003-l004-w003",
"p289-b007-r003-l004-w004",
"p289-b007-r003-l004-w005",
"p289-b007-r003-l004-w006",
"p289-b007-r003-l004-w008",
"p289-b007-r003-l004-w009",
"p289-b007-r003-l004-w010",
"p289-b007-r003-l004-w011",
"p289-b007-r004-l001-w001",
"p289-b007-r004-l001-w002",
"p289-b007-r004-l001-w003",
"p289-b007-r004-l001-w004",
"p289-b007-r004-l001-w005",
"p289-b007-r004-l001-w007",
"p289-b007-r004-l001-w008",
"p289-b007-r004-l001-w009",
"p289-b007-r004-l001-w011",
"p289-b007-r004-l001-w012",
"p289-b007-r004-l001-w013",
"p289-b007-r004-l001-w014",
"p289-b007-r004-l002-w001",
"p289-b007-r004-l002-w003",
"p289-b007-r004-l002-w004",
"p289-b007-r004-l002-w006",
"p289-b007-r004-l002-w007",
"p289-b007-r004-l002-w008",
"p289-b007-r004-l002-w009"
],
"bbox": {
"x": 369,
"y": 1566,
"width": 943,
"height": 327
},
"matched_tokens": 93,
"total_tokens": 106
},
"type": "diary_entry",
"date": {
"date_source": "Monday Oct. 23 - 99",
"date_normalized": "1899-10-23",
"normalization_status": "normalized",
"normalization_confidence": "high",
"normalization_reason": "Expanded the two-digit year and converted the date to ISO format."
},
"place_source": null,
"content": [
{
"id": "p289-b005-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": "Monday Oct. 23 - 99"
}
],
"line_end": "block_end"
}
]
},
{
"id": "p289-b005-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": "Mr. Banks called me early & I had to add a few more loads"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 2,
"segments": [
{
"type": "text",
"text": "to the list - About 9 o'clock the steamer left - we sent"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 3,
"segments": [
{
"type": "text",
"text": "a piece of ham & some bread & cakes with Mr. Banks"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 4,
"segments": [
{
"type": "text",
"text": "Mr. Black gone with him as a passenger. He is strictly"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 5,
"segments": [
{
"type": "text",
"text": "a vegetarian - I don't know how he will get on. Sophie"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 6,
"segments": [
{
"type": "text",
"text": "not well so I could not go over to Kinshasa on boat. I"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 7,
"segments": [
{
"type": "text",
"text": "nearly always go over when a boat leaves. In that way"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 8,
"segments": [
{
"type": "text",
"text": "I keep up with what goes on all around & it saves me a"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 9,
"segments": [
{
"type": "text",
"text": "trip on my wheel or on train one way."
}
],
"line_end": "block_end"
}
]
}
]
}
],
"editorial_notes": [
{
"id": "p289-n001",
"kind": "layout",
"target_block_id": "p289-b001",
"text": "The first nine visible lines form a fully cancelled draft entry; an uncancelled entry for the same date follows.",
"responsibility": "model",
"confidence": "high"
}
],
"provenance": {
"pipeline_version": "0.1.0",
"model_run_id": "20260808T180301Z-eval",
"backend": "codex-exec",
"model": "gpt-5.6-sol",
"reasoning_effort": "xhigh",
"prompt_sha256": "e1b36a5582e8cfa93b0500b53cdffda7937357145c8a02aa053a1beeeeba995a",
"schema_sha256": "a1c29dca3f75ac07c6939242f315bb53cac9c82f75ce42df8aa1c4721bf9f056",
"candidate_sha256": "11dcc5bea1071c336504f92e5b99dc0c3e65ba73d4cd8f94a306cff61a2f9b0b",
"context_pages": [
288,
290
],
"steps": [
{
"kind": "ocr",
"actor": "tesseract 5.5.0",
"artifact": "ocr/page-289.txt",
"created_at": "2026-08-08T18:37:07Z"
},
{
"kind": "model_transcription",
"actor": "codex-exec:gpt-5.6-sol",
"artifact": "20260808T180301Z-eval",
"created_at": "2026-08-08T18:37:07Z"
}
]
},
"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
{
"schema_version": "1.1.0",
"page_id": "page-289",
"source": {
"pdf_page": 289,
"source_pdf_sha256": "80a074ed94fded84fa8a455d61fbf94b25cd4f1239d5ec3e639aaf443467c53f",
"image": {
"path": "pages/page-289.png",
"sha256": "6f943b49e061c8e90fde45fb27a6db8fd596955789e62e7eb307a1afab883569",
"width": 1700,
"height": 2200,
"dpi": 200
},
"ocr": {
"text_path": "ocr/page-289.txt",
"text_sha256": "ee18497cd562b77ce39e497b854923fc2584f74bce016ae16453ebf194cbfa22",
"tsv_path": "ocr/page-289.tsv",
"tsv_sha256": "38a1662b58ba938f5dbf5bf3776d2943bf1c8f591c019e00481a4d7b878e8a40",
"engine": "tesseract 5.5.0"
}
},
"segment": {
"id": "book-05",
"kind": "book",
"label_source": "Last book",
"assignment_status": "inferred"
},
"page_role": "content",
"boundary": {
"starts_mid_block": "no",
"ends_mid_block": "no"
},
"blocks": [
{
"id": "p289-b001",
"order": 1,
"continuation": {
"from_previous": "no",
"to_next": "no",
"previous": null,
"next": null
},
"evidence": {
"status": "unaligned",
"method": null,
"ocr_word_ids": [],
"bbox": null,
"matched_tokens": 0,
"total_tokens": 0
},
"type": "diary_entry",
"date": {
"date_source": "Friday Oct. 20 - 99",
"date_normalized": "1899-10-20",
"normalization_status": "normalized",
"normalization_confidence": "high",
"normalization_reason": "Expanded the two-digit year and converted the date to ISO format."
},
"place_source": null,
"content": [
{
"id": "p289-b001-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": "deletion",
"medium": "handwritten",
"method": "cancelled",
"reading": "Friday Oct. 20 - 99 \"Roi de Belge\"",
"alternatives": [],
"confidence": "high"
}
],
"line_end": "block_end"
}
]
},
{
"id": "p289-b001-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": "deletion",
"medium": "handwritten",
"method": "cancelled",
"reading": "Steamer left - \"Ville-deBruges\" - this a.m. for Kassai",
"alternatives": [],
"confidence": "medium"
}
],
"line_end": "hyphen_lexical"
},
{
"line_number": 2,
"segments": [
{
"type": "deletion",
"medium": "handwritten",
"method": "cancelled",
"reading": "has only charges - hope she will get there o.k. - Sophie",
"alternatives": [],
"confidence": "high"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 3,
"segments": [
{
"type": "deletion",
"medium": "handwritten",
"method": "cancelled",
"reading": "not very well - so did not go to Kinshasa - C.B.M. had",
"alternatives": [],
"confidence": "high"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 4,
"segments": [
{
"type": "deletion",
"medium": "handwritten",
"method": "cancelled",
"reading": "70 loads come in & my boys with theirs had them down by",
"alternatives": [],
"confidence": "high"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 5,
"segments": [
{
"type": "deletion",
"medium": "handwritten",
"method": "cancelled",
"reading": "noon. About it rained a little - Black makes mistakes",
"alternatives": [],
"confidence": "medium"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 6,
"segments": [
{
"type": "deletion",
"medium": "handwritten",
"method": "cancelled",
"reading": "Today Sophie went to Kinshasa in hammock - I went to",
"alternatives": [],
"confidence": "high"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 7,
"segments": [
{
"type": "deletion",
"medium": "handwritten",
"method": "cancelled",
"reading": "Saturday Oct. 21 - 1899 Ndele on train took my bike &",
"alternatives": [],
"confidence": "medium"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 8,
"segments": [
{
"type": "deletion",
"medium": "handwritten",
"method": "cancelled",
"reading": "came back on her - Ate dinner with Gordon & Wife -",
"alternatives": [],
"confidence": "high"
}
],
"line_end": "block_end"
}
]
}
]
},
{
"id": "p289-b002",
"order": 2,
"continuation": {
"from_previous": "no",
"to_next": "no",
"previous": null,
"next": null
},
"evidence": {
"status": "partial",
"method": "exact_normalized_token_sequence",
"ocr_word_ids": [
"p289-b003-r001-l001-w001",
"p289-b003-r001-l001-w002",
"p289-b003-r001-l001-w003",
"p289-b003-r001-l001-w005",
"p289-b003-r001-l002-w002",
"p289-b003-r001-l002-w004",
"p289-b003-r001-l002-w005",
"p289-b003-r001-l002-w008",
"p289-b003-r001-l002-w009",
"p289-b003-r001-l002-w011",
"p289-b003-r001-l002-w012",
"p289-b003-r001-l003-w001",
"p289-b003-r001-l003-w003",
"p289-b003-r001-l003-w004",
"p289-b003-r001-l003-w006",
"p289-b003-r001-l003-w007",
"p289-b003-r001-l003-w008",
"p289-b003-r001-l003-w010",
"p289-b003-r001-l003-w011",
"p289-b003-r001-l003-w012",
"p289-b003-r001-l004-w001",
"p289-b003-r001-l004-w002",
"p289-b003-r001-l004-w003",
"p289-b003-r001-l004-w005",
"p289-b003-r001-l004-w006",
"p289-b003-r001-l004-w007",
"p289-b003-r001-l004-w011",
"p289-b003-r001-l004-w012",
"p289-b003-r001-l005-w001",
"p289-b003-r001-l005-w002",
"p289-b003-r001-l005-w003",
"p289-b003-r001-l005-w005",
"p289-b003-r001-l005-w006",
"p289-b003-r001-l005-w007",
"p289-b003-r001-l005-w008",
"p289-b003-r001-l005-w010",
"p289-b003-r001-l006-w001",
"p289-b003-r001-l006-w002",
"p289-b003-r001-l006-w003",
"p289-b003-r001-l006-w004",
"p289-b003-r001-l006-w008",
"p289-b003-r001-l006-w009",
"p289-b003-r001-l006-w011",
"p289-b003-r001-l007-w001",
"p289-b003-r001-l007-w003",
"p289-b003-r001-l007-w004",
"p289-b003-r001-l007-w005",
"p289-b003-r001-l007-w006",
"p289-b003-r001-l007-w007",
"p289-b003-r001-l007-w008",
"p289-b003-r001-l007-w011",
"p289-b003-r001-l008-w001",
"p289-b003-r001-l008-w002",
"p289-b003-r001-l008-w006",
"p289-b003-r001-l008-w007",
"p289-b003-r001-l008-w008",
"p289-b003-r001-l008-w009",
"p289-b003-r001-l008-w010",
"p289-b003-r001-l008-w011",
"p289-b003-r001-l008-w012",
"p289-b003-r001-l009-w001",
"p289-b003-r001-l009-w002",
"p289-b003-r001-l009-w003",
"p289-b003-r001-l009-w004",
"p289-b003-r001-l009-w005",
"p289-b003-r001-l009-w006",
"p289-b003-r001-l009-w007",
"p289-b003-r001-l009-w008",
"p289-b003-r001-l009-w010",
"p289-b003-r001-l010-w001",
"p289-b003-r001-l010-w002",
"p289-b003-r001-l010-w003",
"p289-b003-r001-l010-w006",
"p289-b003-r001-l010-w007",
"p289-b003-r001-l010-w008"
],
"bbox": {
"x": 371,
"y": 740,
"width": 924,
"height": 328
},
"matched_tokens": 78,
"total_tokens": 101
},
"type": "diary_entry",
"date": {
"date_source": "Friday Oct. 20 - 99",
"date_normalized": "1899-10-20",
"normalization_status": "normalized",
"normalization_confidence": "high",
"normalization_reason": "Expanded the two-digit year and converted the date to ISO format."
},
"place_source": null,
"content": [
{
"id": "p289-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": "Friday Oct. 20 - 99"
}
],
"line_end": "block_end"
}
]
},
{
"id": "p289-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": "Sophie went to Kinshasa in hammock - I went to Ndele on"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 2,
"segments": [
{
"type": "text",
"text": "train took my bike - saw the new bot of CCC Mr. Loyd"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 3,
"segments": [
{
"type": "text",
"text": "is Chief builder - I then came to Gordons & had dinner."
}
],
"line_end": "no_hyphen"
},
{
"line_number": 4,
"segments": [
{
"type": "text",
"text": "Afterwards I went to Dutch House, about 4 o'clock S.S.."
}
],
"line_end": "no_hyphen"
},
{
"line_number": 5,
"segments": [
{
"type": "text",
"text": "Reed came in (A.B.M.U.) & Gordon & I went to the custom"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 6,
"segments": [
{
"type": "text",
"text": "house to meet it, Mr. Banks master. Mrs. Crowley & I"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 7,
"segments": [
{
"type": "text",
"text": "then came down to Leo. with him. He will stay with us"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 8,
"segments": [
{
"type": "text",
"text": "until Monday when he will leave for Hout Congo. Mr."
}
],
"line_end": "no_hyphen"
},
{
"line_number": 9,
"segments": [
{
"type": "text",
"text": "Black has decided to go up with him"
}
],
"line_end": "block_end"
}
]
}
]
},
{
"id": "p289-b003",
"order": 3,
"continuation": {
"from_previous": "no",
"to_next": "no",
"previous": null,
"next": null
},
"evidence": {
"status": "partial",
"method": "exact_normalized_token_sequence",
"ocr_word_ids": [
"p289-b004-r001-l001-w002",
"p289-b004-r001-l001-w003",
"p289-b004-r001-l001-w004",
"p289-b004-r001-l001-w006",
"p289-b004-r002-l001-w001",
"p289-b004-r002-l001-w003",
"p289-b004-r002-l001-w004",
"p289-b004-r002-l001-w005",
"p289-b004-r002-l001-w007",
"p289-b004-r002-l001-w008",
"p289-b004-r002-l001-w010",
"p289-b004-r002-l001-w012",
"p289-b004-r002-l002-w001",
"p289-b004-r002-l002-w002",
"p289-b004-r002-l002-w004",
"p289-b004-r002-l002-w005",
"p289-b004-r002-l002-w006",
"p289-b004-r002-l002-w007",
"p289-b004-r002-l002-w009",
"p289-b004-r002-l002-w010",
"p289-b004-r002-l002-w013",
"p289-b004-r002-l003-w001",
"p289-b004-r002-l003-w003",
"p289-b004-r002-l003-w005",
"p289-b004-r002-l003-w006",
"p289-b004-r002-l003-w007",
"p289-b004-r002-l003-w008",
"p289-b004-r002-l003-w009",
"p289-b004-r002-l003-w010",
"p289-b005-r001-l001-w002",
"p289-b005-r001-l001-w003",
"p289-b005-r001-l001-w004",
"p289-b005-r001-l001-w006",
"p289-b005-r001-l001-w007",
"p289-b005-r001-l001-w009",
"p289-b005-r001-l001-w010",
"p289-b005-r001-l002-w003"
],
"bbox": {
"x": 374,
"y": 1105,
"width": 887,
"height": 184
},
"matched_tokens": 40,
"total_tokens": 54
},
"type": "diary_entry",
"date": {
"date_source": "Saturday Oct. 21 - 99",
"date_normalized": "1899-10-21",
"normalization_status": "normalized",
"normalization_confidence": "high",
"normalization_reason": "Expanded the two-digit year and converted the date to ISO format."
},
"place_source": "Leopoldville",
"content": [
{
"id": "p289-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": "Leopoldville Saturday Oct. 21 - 99"
}
],
"line_end": "block_end"
}
]
},
{
"id": "p289-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": "This a.m. I got out loads for A.B.M.U. & C.B.M. & had"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 2,
"segments": [
{
"type": "text",
"text": "them put on the beach I made out a list &c & sent to"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 3,
"segments": [
{
"type": "text",
"text": "the Custom Officer & had the Extait du Permis signed"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 4,
"segments": [
{
"type": "text",
"text": "a very busy day - packages large & steamer small - Diffi"
}
],
"line_end": "hyphen_word_break"
},
{
"line_number": 5,
"segments": [
{
"type": "text",
"text": "cult to load."
}
],
"line_end": "block_end"
}
]
}
]
},
{
"id": "p289-b004",
"order": 4,
"continuation": {
"from_previous": "no",
"to_next": "no",
"previous": null,
"next": null
},
"evidence": {
"status": "partial",
"method": "exact_normalized_token_sequence",
"ocr_word_ids": [
"p289-b006-r001-l001-w001",
"p289-b006-r001-l001-w002",
"p289-b006-r001-l001-w003",
"p289-b006-r001-l001-w005",
"p289-b006-r002-l001-w001",
"p289-b006-r002-l001-w002",
"p289-b006-r002-l001-w003",
"p289-b006-r002-l001-w004",
"p289-b006-r002-l001-w007",
"p289-b006-r002-l001-w008",
"p289-b006-r002-l001-w009",
"p289-b006-r002-l002-w001",
"p289-b006-r002-l002-w002",
"p289-b006-r002-l002-w003",
"p289-b006-r002-l002-w004",
"p289-b006-r002-l002-w005",
"p289-b006-r002-l002-w007",
"p289-b006-r002-l003-w001",
"p289-b006-r002-l003-w002",
"p289-b006-r002-l003-w003",
"p289-b006-r002-l003-w004",
"p289-b006-r002-l003-w005",
"p289-b006-r002-l003-w006",
"p289-b006-r002-l003-w007",
"p289-b006-r002-l003-w008",
"p289-b006-r002-l003-w009",
"p289-b006-r002-l004-w001",
"p289-b006-r002-l004-w002",
"p289-b006-r002-l004-w003",
"p289-b006-r002-l004-w004",
"p289-b006-r002-l004-w006",
"p289-b006-r002-l004-w009",
"p289-b006-r002-l004-w010",
"p289-b006-r002-l005-w001",
"p289-b006-r002-l005-w003",
"p289-b006-r002-l005-w005"
],
"bbox": {
"x": 374,
"y": 1334,
"width": 920,
"height": 192
},
"matched_tokens": 38,
"total_tokens": 44
},
"type": "diary_entry",
"date": {
"date_source": "Sunday Oct. 22 - 99",
"date_normalized": "1899-10-22",
"normalization_status": "normalized",
"normalization_confidence": "high",
"normalization_reason": "Expanded the two-digit year and converted the date to ISO format."
},
"place_source": null,
"content": [
{
"id": "p289-b004-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": "Sunday Oct. 22 - 99"
}
],
"line_end": "block_end"
}
]
},
{
"id": "p289-b004-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": "Service this a.m. was good - large attendance. Nkaku"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 2,
"segments": [
{
"type": "text",
"text": "Interpreted what I preached to them. Mrs. Crowley's"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 3,
"segments": [
{
"type": "text",
"text": "service in the p.m. was very largely attended. My"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 4,
"segments": [
{
"type": "text",
"text": "service in English was nothing. Prayers for & with the"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 5,
"segments": [
{
"type": "text",
"text": "boys & then to bed."
}
],
"line_end": "block_end"
}
]
}
]
},
{
"id": "p289-b005",
"order": 5,
"continuation": {
"from_previous": "no",
"to_next": "no",
"previous": null,
"next": null
},
"evidence": {
"status": "partial",
"method": "exact_normalized_token_sequence",
"ocr_word_ids": [
"p289-b007-r001-l001-w001",
"p289-b007-r001-l001-w002",
"p289-b007-r001-l001-w003",
"p289-b007-r001-l001-w005",
"p289-b007-r002-l001-w001",
"p289-b007-r002-l001-w002",
"p289-b007-r002-l001-w003",
"p289-b007-r002-l001-w004",
"p289-b007-r002-l001-w005",
"p289-b007-r002-l001-w007",
"p289-b007-r002-l001-w008",
"p289-b007-r002-l001-w009",
"p289-b007-r002-l001-w010",
"p289-b007-r002-l001-w011",
"p289-b007-r002-l001-w012",
"p289-b007-r002-l001-w013",
"p289-b007-r002-l002-w002",
"p289-b007-r002-l002-w003",
"p289-b007-r002-l002-w005",
"p289-b007-r002-l002-w006",
"p289-b007-r002-l002-w008",
"p289-b007-r002-l002-w009",
"p289-b007-r002-l002-w010",
"p289-b007-r002-l002-w012",
"p289-b007-r002-l002-w013",
"p289-b007-r002-l003-w001",
"p289-b007-r002-l003-w002",
"p289-b007-r002-l003-w003",
"p289-b007-r002-l003-w004",
"p289-b007-r002-l003-w006",
"p289-b007-r002-l003-w007",
"p289-b007-r002-l003-w009",
"p289-b007-r002-l003-w010",
"p289-b007-r002-l003-w011",
"p289-b007-r002-l003-w012",
"p289-b007-r003-l001-w001",
"p289-b007-r003-l001-w002",
"p289-b007-r003-l001-w003",
"p289-b007-r003-l001-w004",
"p289-b007-r003-l001-w005",
"p289-b007-r003-l001-w006",
"p289-b007-r003-l001-w007",
"p289-b007-r003-l001-w008",
"p289-b007-r003-l001-w009",
"p289-b007-r003-l001-w010",
"p289-b007-r003-l001-w011",
"p289-b007-r003-l002-w001",
"p289-b007-r003-l002-w002",
"p289-b007-r003-l002-w004",
"p289-b007-r003-l002-w006",
"p289-b007-r003-l002-w007",
"p289-b007-r003-l002-w008",
"p289-b007-r003-l002-w009",
"p289-b007-r003-l002-w010",
"p289-b007-r003-l002-w011",
"p289-b007-r003-l002-w012",
"p289-b007-r003-l003-w002",
"p289-b007-r003-l003-w003",
"p289-b007-r003-l003-w004",
"p289-b007-r003-l003-w005",
"p289-b007-r003-l003-w007",
"p289-b007-r003-l003-w009",
"p289-b007-r003-l003-w010",
"p289-b007-r003-l003-w013",
"p289-b007-r003-l004-w001",
"p289-b007-r003-l004-w002",
"p289-b007-r003-l004-w003",
"p289-b007-r003-l004-w004",
"p289-b007-r003-l004-w005",
"p289-b007-r003-l004-w006",
"p289-b007-r003-l004-w008",
"p289-b007-r003-l004-w009",
"p289-b007-r003-l004-w010",
"p289-b007-r003-l004-w011",
"p289-b007-r004-l001-w001",
"p289-b007-r004-l001-w002",
"p289-b007-r004-l001-w003",
"p289-b007-r004-l001-w004",
"p289-b007-r004-l001-w005",
"p289-b007-r004-l001-w007",
"p289-b007-r004-l001-w008",
"p289-b007-r004-l001-w009",
"p289-b007-r004-l001-w011",
"p289-b007-r004-l001-w012",
"p289-b007-r004-l001-w013",
"p289-b007-r004-l001-w014",
"p289-b007-r004-l002-w001",
"p289-b007-r004-l002-w003",
"p289-b007-r004-l002-w004",
"p289-b007-r004-l002-w006",
"p289-b007-r004-l002-w007",
"p289-b007-r004-l002-w008",
"p289-b007-r004-l002-w009"
],
"bbox": {
"x": 369,
"y": 1566,
"width": 943,
"height": 327
},
"matched_tokens": 93,
"total_tokens": 106
},
"type": "diary_entry",
"date": {
"date_source": "Monday Oct. 23 - 99",
"date_normalized": "1899-10-23",
"normalization_status": "normalized",
"normalization_confidence": "high",
"normalization_reason": "Expanded the two-digit year and converted the date to ISO format."
},
"place_source": null,
"content": [
{
"id": "p289-b005-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": "Monday Oct. 23 - 99"
}
],
"line_end": "block_end"
}
]
},
{
"id": "p289-b005-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": "Mr. Banks called me early & I had to add a few more loads"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 2,
"segments": [
{
"type": "text",
"text": "to the list - About 9 o'clock the steamer left - we sent"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 3,
"segments": [
{
"type": "text",
"text": "a piece of ham & some bread & cakes with Mr. Banks"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 4,
"segments": [
{
"type": "text",
"text": "Mr. Black gone with him as a passenger. He is strictly"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 5,
"segments": [
{
"type": "text",
"text": "a vegetarian - I don't know how he will get on. Sophie"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 6,
"segments": [
{
"type": "text",
"text": "not well so I could not go over to Kinshasa on boat. I"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 7,
"segments": [
{
"type": "text",
"text": "nearly always go over when a boat leaves. In that way"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 8,
"segments": [
{
"type": "text",
"text": "I keep up with what goes on all around & it saves me a"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 9,
"segments": [
{
"type": "text",
"text": "trip on my wheel or on train one way."
}
],
"line_end": "block_end"
}
]
}
]
}
],
"editorial_notes": [
{
"id": "p289-n001",
"kind": "layout",
"target_block_id": "p289-b001",
"text": "The first nine visible lines form a fully cancelled draft entry; an uncancelled entry for the same date follows.",
"responsibility": "model",
"confidence": "high"
}
],
"provenance": {
"pipeline_version": "0.1.0",
"model_run_id": "20260808T180301Z-eval",
"backend": "codex-exec",
"model": "gpt-5.6-sol",
"reasoning_effort": "xhigh",
"prompt_sha256": "e1b36a5582e8cfa93b0500b53cdffda7937357145c8a02aa053a1beeeeba995a",
"schema_sha256": "a1c29dca3f75ac07c6939242f315bb53cac9c82f75ce42df8aa1c4721bf9f056",
"candidate_sha256": "11dcc5bea1071c336504f92e5b99dc0c3e65ba73d4cd8f94a306cff61a2f9b0b",
"context_pages": [
288,
290
],
"steps": [
{
"kind": "ocr",
"actor": "tesseract 5.5.0",
"artifact": "ocr/page-289.txt",
"created_at": "2026-08-08T18:37:07Z"
},
{
"kind": "model_transcription",
"actor": "codex-exec:gpt-5.6-sol",
"artifact": "20260808T180301Z-eval",
"created_at": "2026-08-08T18:37:07Z"
},
{
"kind": "agent_review",
"actor": "Codex",
"artifact": "artifacts/runs/20260808T180301Z-eval/candidates/page-289.json",
"created_at": "2026-08-08T18:38:26Z"
}
]
},
"review": {
"status": "agent_reviewed",
"authority": "diagnostic_only",
"reviewer": "Codex",
"reviewed_at": "2026-08-08T18:38:26Z",
"notes": [
"Diagnostic fixture only; it is not independent ground truth and has not been owner-approved.",
"Compared the fully cancelled top passage and the retyped Friday-through-Monday entries against the authoritative page image.",
"No text changes were required. The diagnostic retains the cancelled top region as one draft diary block even though a struck Saturday heading occurs inside it; this is a documented schema/segmentation ambiguity."
]
}
}Owner-approved edition JSON
{
"schema_version": "1.1.0",
"page_id": "page-289",
"source": {
"pdf_page": 289,
"source_pdf_sha256": "80a074ed94fded84fa8a455d61fbf94b25cd4f1239d5ec3e639aaf443467c53f",
"image": {
"path": "pages/page-289.png",
"sha256": "6f943b49e061c8e90fde45fb27a6db8fd596955789e62e7eb307a1afab883569",
"width": 1700,
"height": 2200,
"dpi": 200
},
"ocr": {
"text_path": "ocr/page-289.txt",
"text_sha256": "ee18497cd562b77ce39e497b854923fc2584f74bce016ae16453ebf194cbfa22",
"tsv_path": "ocr/page-289.tsv",
"tsv_sha256": "38a1662b58ba938f5dbf5bf3776d2943bf1c8f591c019e00481a4d7b878e8a40",
"engine": "tesseract 5.5.0"
}
},
"segment": {
"id": "book-05",
"kind": "book",
"label_source": "Last book",
"assignment_status": "inferred"
},
"page_role": "content",
"boundary": {
"starts_mid_block": "no",
"ends_mid_block": "no"
},
"blocks": [
{
"id": "p289-b001",
"order": 1,
"continuation": {
"from_previous": "no",
"to_next": "no",
"previous": null,
"next": null
},
"evidence": {
"status": "unaligned",
"method": null,
"ocr_word_ids": [],
"bbox": null,
"matched_tokens": 0,
"total_tokens": 0
},
"type": "diary_entry",
"date": {
"date_source": "Friday Oct. 20 - 99",
"date_normalized": "1899-10-20",
"normalization_status": "normalized",
"normalization_confidence": "high",
"normalization_reason": "Expanded the two-digit year and converted the date to ISO format."
},
"place_source": null,
"content": [
{
"id": "p289-b001-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": "deletion",
"medium": "handwritten",
"method": "cancelled",
"reading": "Friday Oct. 20 - 99 \"Roi de Belge\"",
"alternatives": [],
"confidence": "high"
}
],
"line_end": "block_end"
}
]
},
{
"id": "p289-b001-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": "deletion",
"medium": "handwritten",
"method": "cancelled",
"reading": "Steamer left - \"Ville-deBruges\" - this a.m. for Kassai",
"alternatives": [],
"confidence": "medium"
}
],
"line_end": "hyphen_lexical"
},
{
"line_number": 2,
"segments": [
{
"type": "deletion",
"medium": "handwritten",
"method": "cancelled",
"reading": "has only charges - hope she will get there o.k. - Sophie",
"alternatives": [],
"confidence": "high"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 3,
"segments": [
{
"type": "deletion",
"medium": "handwritten",
"method": "cancelled",
"reading": "not very well - so did not go to Kinshasa - C.B.M. had",
"alternatives": [],
"confidence": "high"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 4,
"segments": [
{
"type": "deletion",
"medium": "handwritten",
"method": "cancelled",
"reading": "70 loads come in & my boys with theirs had them down by",
"alternatives": [],
"confidence": "high"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 5,
"segments": [
{
"type": "deletion",
"medium": "handwritten",
"method": "cancelled",
"reading": "noon. About it rained a little - Black makes mistakes",
"alternatives": [],
"confidence": "medium"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 6,
"segments": [
{
"type": "deletion",
"medium": "handwritten",
"method": "cancelled",
"reading": "Today Sophie went to Kinshasa in hammock - I went to",
"alternatives": [],
"confidence": "high"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 7,
"segments": [
{
"type": "deletion",
"medium": "handwritten",
"method": "cancelled",
"reading": "Saturday Oct. 21 - 1899 Ndele on train took my bike &",
"alternatives": [],
"confidence": "medium"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 8,
"segments": [
{
"type": "deletion",
"medium": "handwritten",
"method": "cancelled",
"reading": "came back on her - Ate dinner with Gordon & Wife -",
"alternatives": [],
"confidence": "high"
}
],
"line_end": "block_end"
}
]
}
]
},
{
"id": "p289-b002",
"order": 2,
"continuation": {
"from_previous": "no",
"to_next": "no",
"previous": null,
"next": null
},
"evidence": {
"status": "partial",
"method": "exact_normalized_token_sequence",
"ocr_word_ids": [
"p289-b003-r001-l001-w001",
"p289-b003-r001-l001-w002",
"p289-b003-r001-l001-w003",
"p289-b003-r001-l001-w005",
"p289-b003-r001-l002-w002",
"p289-b003-r001-l002-w004",
"p289-b003-r001-l002-w005",
"p289-b003-r001-l002-w008",
"p289-b003-r001-l002-w009",
"p289-b003-r001-l002-w011",
"p289-b003-r001-l002-w012",
"p289-b003-r001-l003-w001",
"p289-b003-r001-l003-w003",
"p289-b003-r001-l003-w004",
"p289-b003-r001-l003-w006",
"p289-b003-r001-l003-w007",
"p289-b003-r001-l003-w008",
"p289-b003-r001-l003-w010",
"p289-b003-r001-l003-w011",
"p289-b003-r001-l003-w012",
"p289-b003-r001-l004-w001",
"p289-b003-r001-l004-w002",
"p289-b003-r001-l004-w003",
"p289-b003-r001-l004-w005",
"p289-b003-r001-l004-w006",
"p289-b003-r001-l004-w007",
"p289-b003-r001-l004-w011",
"p289-b003-r001-l004-w012",
"p289-b003-r001-l005-w001",
"p289-b003-r001-l005-w002",
"p289-b003-r001-l005-w003",
"p289-b003-r001-l005-w005",
"p289-b003-r001-l005-w006",
"p289-b003-r001-l005-w007",
"p289-b003-r001-l005-w008",
"p289-b003-r001-l005-w010",
"p289-b003-r001-l006-w001",
"p289-b003-r001-l006-w002",
"p289-b003-r001-l006-w003",
"p289-b003-r001-l006-w004",
"p289-b003-r001-l006-w008",
"p289-b003-r001-l006-w009",
"p289-b003-r001-l006-w011",
"p289-b003-r001-l007-w001",
"p289-b003-r001-l007-w003",
"p289-b003-r001-l007-w004",
"p289-b003-r001-l007-w005",
"p289-b003-r001-l007-w006",
"p289-b003-r001-l007-w007",
"p289-b003-r001-l007-w008",
"p289-b003-r001-l007-w011",
"p289-b003-r001-l008-w001",
"p289-b003-r001-l008-w002",
"p289-b003-r001-l008-w006",
"p289-b003-r001-l008-w007",
"p289-b003-r001-l008-w008",
"p289-b003-r001-l008-w009",
"p289-b003-r001-l008-w010",
"p289-b003-r001-l008-w011",
"p289-b003-r001-l008-w012",
"p289-b003-r001-l009-w001",
"p289-b003-r001-l009-w002",
"p289-b003-r001-l009-w003",
"p289-b003-r001-l009-w004",
"p289-b003-r001-l009-w005",
"p289-b003-r001-l009-w006",
"p289-b003-r001-l009-w007",
"p289-b003-r001-l009-w008",
"p289-b003-r001-l009-w010",
"p289-b003-r001-l010-w001",
"p289-b003-r001-l010-w002",
"p289-b003-r001-l010-w003",
"p289-b003-r001-l010-w006",
"p289-b003-r001-l010-w007",
"p289-b003-r001-l010-w008"
],
"bbox": {
"x": 371,
"y": 740,
"width": 924,
"height": 328
},
"matched_tokens": 78,
"total_tokens": 101
},
"type": "diary_entry",
"date": {
"date_source": "Friday Oct. 20 - 99",
"date_normalized": "1899-10-20",
"normalization_status": "normalized",
"normalization_confidence": "high",
"normalization_reason": "Expanded the two-digit year and converted the date to ISO format."
},
"place_source": null,
"content": [
{
"id": "p289-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": "Friday Oct. 20 - 99"
}
],
"line_end": "block_end"
}
]
},
{
"id": "p289-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": "Sophie went to Kinshasa in hammock - I went to Ndele on"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 2,
"segments": [
{
"type": "text",
"text": "train took my bike - saw the new bot of CCC Mr. Loyd"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 3,
"segments": [
{
"type": "text",
"text": "is Chief builder - I then came to Gordons & had dinner."
}
],
"line_end": "no_hyphen"
},
{
"line_number": 4,
"segments": [
{
"type": "text",
"text": "Afterwards I went to Dutch House, about 4 o'clock S.S.."
}
],
"line_end": "no_hyphen"
},
{
"line_number": 5,
"segments": [
{
"type": "text",
"text": "Reed came in (A.B.M.U.) & Gordon & I went to the custom"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 6,
"segments": [
{
"type": "text",
"text": "house to meet it, Mr. Banks master. Mrs. Crowley & I"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 7,
"segments": [
{
"type": "text",
"text": "then came down to Leo. with him. He will stay with us"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 8,
"segments": [
{
"type": "text",
"text": "until Monday when he will leave for Hout Congo. Mr."
}
],
"line_end": "no_hyphen"
},
{
"line_number": 9,
"segments": [
{
"type": "text",
"text": "Black has decided to go up with him"
}
],
"line_end": "block_end"
}
]
}
]
},
{
"id": "p289-b003",
"order": 3,
"continuation": {
"from_previous": "no",
"to_next": "no",
"previous": null,
"next": null
},
"evidence": {
"status": "partial",
"method": "exact_normalized_token_sequence",
"ocr_word_ids": [
"p289-b004-r001-l001-w002",
"p289-b004-r001-l001-w003",
"p289-b004-r001-l001-w004",
"p289-b004-r001-l001-w006",
"p289-b004-r002-l001-w001",
"p289-b004-r002-l001-w003",
"p289-b004-r002-l001-w004",
"p289-b004-r002-l001-w005",
"p289-b004-r002-l001-w007",
"p289-b004-r002-l001-w008",
"p289-b004-r002-l001-w010",
"p289-b004-r002-l001-w012",
"p289-b004-r002-l002-w001",
"p289-b004-r002-l002-w002",
"p289-b004-r002-l002-w004",
"p289-b004-r002-l002-w005",
"p289-b004-r002-l002-w006",
"p289-b004-r002-l002-w007",
"p289-b004-r002-l002-w009",
"p289-b004-r002-l002-w010",
"p289-b004-r002-l002-w013",
"p289-b004-r002-l003-w001",
"p289-b004-r002-l003-w003",
"p289-b004-r002-l003-w005",
"p289-b004-r002-l003-w006",
"p289-b004-r002-l003-w007",
"p289-b004-r002-l003-w008",
"p289-b004-r002-l003-w009",
"p289-b004-r002-l003-w010",
"p289-b005-r001-l001-w002",
"p289-b005-r001-l001-w003",
"p289-b005-r001-l001-w004",
"p289-b005-r001-l001-w006",
"p289-b005-r001-l001-w007",
"p289-b005-r001-l001-w009",
"p289-b005-r001-l001-w010",
"p289-b005-r001-l002-w003"
],
"bbox": {
"x": 374,
"y": 1105,
"width": 887,
"height": 184
},
"matched_tokens": 40,
"total_tokens": 54
},
"type": "diary_entry",
"date": {
"date_source": "Saturday Oct. 21 - 99",
"date_normalized": "1899-10-21",
"normalization_status": "normalized",
"normalization_confidence": "high",
"normalization_reason": "Expanded the two-digit year and converted the date to ISO format."
},
"place_source": "Leopoldville",
"content": [
{
"id": "p289-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": "Leopoldville Saturday Oct. 21 - 99"
}
],
"line_end": "block_end"
}
]
},
{
"id": "p289-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": "This a.m. I got out loads for A.B.M.U. & C.B.M. & had"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 2,
"segments": [
{
"type": "text",
"text": "them put on the beach I made out a list &c & sent to"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 3,
"segments": [
{
"type": "text",
"text": "the Custom Officer & had the Extait du Permis signed"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 4,
"segments": [
{
"type": "text",
"text": "a very busy day - packages large & steamer small - Diffi"
}
],
"line_end": "hyphen_word_break"
},
{
"line_number": 5,
"segments": [
{
"type": "text",
"text": "cult to load."
}
],
"line_end": "block_end"
}
]
}
]
},
{
"id": "p289-b004",
"order": 4,
"continuation": {
"from_previous": "no",
"to_next": "no",
"previous": null,
"next": null
},
"evidence": {
"status": "partial",
"method": "exact_normalized_token_sequence",
"ocr_word_ids": [
"p289-b006-r001-l001-w001",
"p289-b006-r001-l001-w002",
"p289-b006-r001-l001-w003",
"p289-b006-r001-l001-w005",
"p289-b006-r002-l001-w001",
"p289-b006-r002-l001-w002",
"p289-b006-r002-l001-w003",
"p289-b006-r002-l001-w004",
"p289-b006-r002-l001-w007",
"p289-b006-r002-l001-w008",
"p289-b006-r002-l001-w009",
"p289-b006-r002-l002-w001",
"p289-b006-r002-l002-w002",
"p289-b006-r002-l002-w003",
"p289-b006-r002-l002-w004",
"p289-b006-r002-l002-w005",
"p289-b006-r002-l002-w007",
"p289-b006-r002-l003-w001",
"p289-b006-r002-l003-w002",
"p289-b006-r002-l003-w003",
"p289-b006-r002-l003-w004",
"p289-b006-r002-l003-w005",
"p289-b006-r002-l003-w006",
"p289-b006-r002-l003-w007",
"p289-b006-r002-l003-w008",
"p289-b006-r002-l003-w009",
"p289-b006-r002-l004-w001",
"p289-b006-r002-l004-w002",
"p289-b006-r002-l004-w003",
"p289-b006-r002-l004-w004",
"p289-b006-r002-l004-w006",
"p289-b006-r002-l004-w009",
"p289-b006-r002-l004-w010",
"p289-b006-r002-l005-w001",
"p289-b006-r002-l005-w003",
"p289-b006-r002-l005-w005"
],
"bbox": {
"x": 374,
"y": 1334,
"width": 920,
"height": 192
},
"matched_tokens": 38,
"total_tokens": 44
},
"type": "diary_entry",
"date": {
"date_source": "Sunday Oct. 22 - 99",
"date_normalized": "1899-10-22",
"normalization_status": "normalized",
"normalization_confidence": "high",
"normalization_reason": "Expanded the two-digit year and converted the date to ISO format."
},
"place_source": null,
"content": [
{
"id": "p289-b004-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": "Sunday Oct. 22 - 99"
}
],
"line_end": "block_end"
}
]
},
{
"id": "p289-b004-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": "Service this a.m. was good - large attendance. Nkaku"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 2,
"segments": [
{
"type": "text",
"text": "Interpreted what I preached to them. Mrs. Crowley's"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 3,
"segments": [
{
"type": "text",
"text": "service in the p.m. was very largely attended. My"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 4,
"segments": [
{
"type": "text",
"text": "service in English was nothing. Prayers for & with the"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 5,
"segments": [
{
"type": "text",
"text": "boys & then to bed."
}
],
"line_end": "block_end"
}
]
}
]
},
{
"id": "p289-b005",
"order": 5,
"continuation": {
"from_previous": "no",
"to_next": "no",
"previous": null,
"next": null
},
"evidence": {
"status": "partial",
"method": "exact_normalized_token_sequence",
"ocr_word_ids": [
"p289-b007-r001-l001-w001",
"p289-b007-r001-l001-w002",
"p289-b007-r001-l001-w003",
"p289-b007-r001-l001-w005",
"p289-b007-r002-l001-w001",
"p289-b007-r002-l001-w002",
"p289-b007-r002-l001-w003",
"p289-b007-r002-l001-w004",
"p289-b007-r002-l001-w005",
"p289-b007-r002-l001-w007",
"p289-b007-r002-l001-w008",
"p289-b007-r002-l001-w009",
"p289-b007-r002-l001-w010",
"p289-b007-r002-l001-w011",
"p289-b007-r002-l001-w012",
"p289-b007-r002-l001-w013",
"p289-b007-r002-l002-w002",
"p289-b007-r002-l002-w003",
"p289-b007-r002-l002-w005",
"p289-b007-r002-l002-w006",
"p289-b007-r002-l002-w008",
"p289-b007-r002-l002-w009",
"p289-b007-r002-l002-w010",
"p289-b007-r002-l002-w012",
"p289-b007-r002-l002-w013",
"p289-b007-r002-l003-w001",
"p289-b007-r002-l003-w002",
"p289-b007-r002-l003-w003",
"p289-b007-r002-l003-w004",
"p289-b007-r002-l003-w006",
"p289-b007-r002-l003-w007",
"p289-b007-r002-l003-w009",
"p289-b007-r002-l003-w010",
"p289-b007-r002-l003-w011",
"p289-b007-r002-l003-w012",
"p289-b007-r003-l001-w001",
"p289-b007-r003-l001-w002",
"p289-b007-r003-l001-w003",
"p289-b007-r003-l001-w004",
"p289-b007-r003-l001-w005",
"p289-b007-r003-l001-w006",
"p289-b007-r003-l001-w007",
"p289-b007-r003-l001-w008",
"p289-b007-r003-l001-w009",
"p289-b007-r003-l001-w010",
"p289-b007-r003-l001-w011",
"p289-b007-r003-l002-w001",
"p289-b007-r003-l002-w002",
"p289-b007-r003-l002-w004",
"p289-b007-r003-l002-w006",
"p289-b007-r003-l002-w007",
"p289-b007-r003-l002-w008",
"p289-b007-r003-l002-w009",
"p289-b007-r003-l002-w010",
"p289-b007-r003-l002-w011",
"p289-b007-r003-l002-w012",
"p289-b007-r003-l003-w002",
"p289-b007-r003-l003-w003",
"p289-b007-r003-l003-w004",
"p289-b007-r003-l003-w005",
"p289-b007-r003-l003-w007",
"p289-b007-r003-l003-w009",
"p289-b007-r003-l003-w010",
"p289-b007-r003-l003-w013",
"p289-b007-r003-l004-w001",
"p289-b007-r003-l004-w002",
"p289-b007-r003-l004-w003",
"p289-b007-r003-l004-w004",
"p289-b007-r003-l004-w005",
"p289-b007-r003-l004-w006",
"p289-b007-r003-l004-w008",
"p289-b007-r003-l004-w009",
"p289-b007-r003-l004-w010",
"p289-b007-r003-l004-w011",
"p289-b007-r004-l001-w001",
"p289-b007-r004-l001-w002",
"p289-b007-r004-l001-w003",
"p289-b007-r004-l001-w004",
"p289-b007-r004-l001-w005",
"p289-b007-r004-l001-w007",
"p289-b007-r004-l001-w008",
"p289-b007-r004-l001-w009",
"p289-b007-r004-l001-w011",
"p289-b007-r004-l001-w012",
"p289-b007-r004-l001-w013",
"p289-b007-r004-l001-w014",
"p289-b007-r004-l002-w001",
"p289-b007-r004-l002-w003",
"p289-b007-r004-l002-w004",
"p289-b007-r004-l002-w006",
"p289-b007-r004-l002-w007",
"p289-b007-r004-l002-w008",
"p289-b007-r004-l002-w009"
],
"bbox": {
"x": 369,
"y": 1566,
"width": 943,
"height": 327
},
"matched_tokens": 93,
"total_tokens": 106
},
"type": "diary_entry",
"date": {
"date_source": "Monday Oct. 23 - 99",
"date_normalized": "1899-10-23",
"normalization_status": "normalized",
"normalization_confidence": "high",
"normalization_reason": "Expanded the two-digit year and converted the date to ISO format."
},
"place_source": null,
"content": [
{
"id": "p289-b005-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": "Monday Oct. 23 - 99"
}
],
"line_end": "block_end"
}
]
},
{
"id": "p289-b005-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": "Mr. Banks called me early & I had to add a few more loads"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 2,
"segments": [
{
"type": "text",
"text": "to the list - About 9 o'clock the steamer left - we sent"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 3,
"segments": [
{
"type": "text",
"text": "a piece of ham & some bread & cakes with Mr. Banks"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 4,
"segments": [
{
"type": "text",
"text": "Mr. Black gone with him as a passenger. He is strictly"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 5,
"segments": [
{
"type": "text",
"text": "a vegetarian - I don't know how he will get on. Sophie"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 6,
"segments": [
{
"type": "text",
"text": "not well so I could not go over to Kinshasa on boat. I"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 7,
"segments": [
{
"type": "text",
"text": "nearly always go over when a boat leaves. In that way"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 8,
"segments": [
{
"type": "text",
"text": "I keep up with what goes on all around & it saves me a"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 9,
"segments": [
{
"type": "text",
"text": "trip on my wheel or on train one way."
}
],
"line_end": "block_end"
}
]
}
]
}
],
"editorial_notes": [
{
"id": "p289-n001",
"kind": "layout",
"target_block_id": "p289-b001",
"text": "The first nine visible lines form a fully cancelled draft entry; an uncancelled entry for the same date follows.",
"responsibility": "model",
"confidence": "high"
}
],
"provenance": {
"pipeline_version": "0.1.0",
"model_run_id": "20260808T180301Z-eval",
"backend": "codex-exec",
"model": "gpt-5.6-sol",
"reasoning_effort": "xhigh",
"prompt_sha256": "e1b36a5582e8cfa93b0500b53cdffda7937357145c8a02aa053a1beeeeba995a",
"schema_sha256": "a1c29dca3f75ac07c6939242f315bb53cac9c82f75ce42df8aa1c4721bf9f056",
"candidate_sha256": "11dcc5bea1071c336504f92e5b99dc0c3e65ba73d4cd8f94a306cff61a2f9b0b",
"context_pages": [
288,
290
],
"steps": [
{
"kind": "ocr",
"actor": "tesseract 5.5.0",
"artifact": "ocr/page-289.txt",
"created_at": "2026-08-08T18:37:07Z"
},
{
"kind": "model_transcription",
"actor": "codex-exec:gpt-5.6-sol",
"artifact": "20260808T180301Z-eval",
"created_at": "2026-08-08T18:37:07Z"
},
{
"kind": "agent_review",
"actor": "Codex",
"artifact": "artifacts/runs/20260808T180301Z-eval/candidates/page-289.json",
"created_at": "2026-08-08T18:38:26Z"
},
{
"kind": "owner_review",
"actor": "John Crowley",
"artifact": "evaluation/goldens/page-289.json",
"created_at": "2026-08-08T20:02:49Z",
"action": "approve_as_is",
"input_sha256": "686ee1ebe1fbe83e934fef1ed9f76c74d25989cfd980e0211648d759120dcd65",
"change_categories": []
}
]
},
"review": {
"status": "owner_approved",
"authority": "owner_approved_edition",
"reviewer": "John Crowley",
"reviewed_at": "2026-08-08T20:02:49Z",
"notes": [
"Diagnostic fixture only; it is not independent ground truth and has not been owner-approved.",
"Compared the fully cancelled top passage and the retyped Friday-through-Monday entries against the authoritative page image.",
"No text changes were required. The diagnostic retains the cancelled top region as one draft diary block even though a struck Saturday heading occurs inside it; this is a documented schema/segmentation ambiguity.",
"Explicit owner action: approve_as_is.",
"Approval lineage begins with diagnostic SHA-256 686ee1ebe1fbe83e934fef1ed9f76c74d25989cfd980e0211648d759120dcd65.",
"Owner visually compared the diagnostic with the authoritative scan and approved it without further changes."
]
}
}