Triple
T25407950
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Academy Award for Best Actor for "Life with Father" |
E636607
|
entity |
| Predicate | relatedFilmDirector |
P46692
|
FINISHED |
| Object | Michael Curtiz |
—
|
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: Michael Curtiz | Statement: [Academy Award for Best Actor for "Life with Father", relatedFilmDirector, Michael Curtiz]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relatedFilmDirector Context triple: [Academy Award for Best Actor for "Life with Father", relatedFilmDirector, Michael Curtiz]
-
A.
filmDirectorOfAssociatedWork
Indicates that a person serves as the director of the specified creative work (such as a film or related audiovisual production).
-
B.
filmDirectorWorkedWith
Indicates that a film director has collaborated professionally with another person on one or more film projects.
-
C.
appearedInFilmDirectedBy
Indicates that an entity appeared in a film whose director is the specified other entity.
-
D.
directorsOfFilm
chosen
Indicates the person or people who directed a given film.
-
E.
filmDirectorOfWorkAppearsIn
Indicates that a person is the director of a film in which a particular work (e.g., book, play, or other source material) appears or is featured.
- 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_69e75db361d881908d8701c856da6413 |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f7be53890081909b1d93f30a8f31c6 |
completed | May 3, 2026, 9:29 p.m. |
| PD | Predicate disambiguation | batch_69f7bccacbac8190978976324c67db28 |
completed | May 3, 2026, 9:23 p.m. |
Created at: April 21, 2026, 1:52 p.m.