Triple
T29610817
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Audrey in Rome |
E754713
|
entity |
| Predicate | hasPhotographsOf |
P104022
|
FINISHED |
| Object | Audrey Hepburn |
—
|
NE NERFINISHED |
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: Audrey Hepburn | Statement: [Audrey in Rome, hasPhotographsOf, Audrey Hepburn]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPhotographsOf Context triple: [Audrey in Rome, hasPhotographsOf, Audrey Hepburn]
-
A.
hasPhotographs
chosen
Indicates that one entity possesses, contains, or is associated with one or more photographs of another entity or subject.
-
B.
hasPhotographBy
Indicates that an entity is depicted in or associated with a photograph that was created or taken by a specified photographer.
-
C.
hasPhotograph
Indicates that one entity possesses, includes, or is associated with a photograph depicting or representing another entity.
-
D.
hasPhotographedFor
Indicates that one entity has taken photographs on behalf of, or as a service for, another entity.
-
E.
hasPhotographicCollectionAt
Indicates that an entity maintains or possesses a photographic collection located at a specified place or institution.
- 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_69f0ef85f62081909842b59fdf8717e1 |
completed | April 28, 2026, 5:33 p.m. |
| NER | Named-entity recognition | batch_69f6b49436b0819094e21603054d05d4 |
completed | May 3, 2026, 2:36 a.m. |
| PD | Predicate disambiguation | batch_69f6b3a5fd8481909433e923c5e24e55 |
completed | May 3, 2026, 2:32 a.m. |
Created at: April 28, 2026, 6:28 p.m.