Triple
T22950332
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | BNF bibliographic database |
E569995
|
entity |
| Predicate | isCatalogOf |
P88854
|
FINISHED |
| Object | Bibliothèque nationale de France collections |
—
|
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: Bibliothèque nationale de France collections | Statement: [BNF bibliographic database, isCatalogOf, Bibliothèque nationale de France collections]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isCatalogOf Context triple: [BNF bibliographic database, isCatalogOf, Bibliothèque nationale de France collections]
-
A.
belongsToCatalogOf
Indicates that one item is included within, or is a member of, a particular catalog or collection.
-
B.
catalogueFor
chosen
Indicates that one entity serves as a catalog or organized listing that describes, indexes, or inventories another entity.
-
C.
hasCatalogView
Indicates that an entity is associated with a particular way or mode of viewing or presenting a catalog.
-
D.
catalogedBy
Indicates that an item or resource has been organized, described, or recorded in a catalog by a particular agent or system.
-
E.
subjectOfCatalog
Indicates that something is the primary focus or entry described within a catalog or cataloging record.
- 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_69e2459199d08190a8184ee2aa935842 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f181a1b334819097a4e9ea8a54209c |
completed | April 29, 2026, 3:57 a.m. |
| PD | Predicate disambiguation | batch_69ef3b882e708190b0eb0c87021c75b8 |
completed | April 27, 2026, 10:33 a.m. |
Created at: April 17, 2026, 3:46 p.m.