Triple
T28722571
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | P. Chester Beatty II |
E730133
|
entity |
| Predicate | originalFolioCount |
P20098
|
FINISHED |
| Object | approximately 104 leaves |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: approximately 104 leaves | Statement: [P. Chester Beatty II, originalFolioCount, approximately 104 leaves]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originalFolioCount Context triple: [P. Chester Beatty II, originalFolioCount, approximately 104 leaves]
-
A.
hasFolioNumbers
Indicates that an item (such as a manuscript or document) possesses assigned folio numbers identifying its individual leaves or pages.
-
B.
pageCountFirstEdition
Indicates the number of pages contained in the first edition of an item.
-
C.
originalCatalogNumberFor
Indicates that one resource is the original catalog number assigned to another resource.
-
D.
originalNumberOfLeaves
chosen
Indicates the initial count of leaves associated with an entity before any changes, losses, or additions occur.
-
E.
hasOriginalWorkVolumeNumber
Indicates the association between a work (or its edition) and the volume number it had in the original multi-volume publication.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69f043e91fe48190b73bcd8e08d433e0 |
completed | April 28, 2026, 5:21 a.m. |
| NER | Named-entity recognition | batch_69ff109695008190a22b47ef8be2e3f9 |
completed | May 9, 2026, 10:46 a.m. |
| PD | Predicate disambiguation | batch_69ff0f243ea88190970d2c520b55c816 |
completed | May 9, 2026, 10:40 a.m. |
Created at: April 28, 2026, 5:54 a.m.