Triple
T31050343
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Academy Award for Best Director for Johnny Belinda |
E791243
|
entity |
| Predicate | winnerDirectorInCategory |
P37391
|
FINISHED |
| Object | John Huston |
—
|
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: John Huston | Statement: [Academy Award for Best Director for Johnny Belinda, winnerDirectorInCategory, John Huston]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: winnerDirectorInCategory Context triple: [Academy Award for Best Director for Johnny Belinda, winnerDirectorInCategory, John Huston]
-
A.
bestDirectorWinner
Indicates that the subject is the winner of a "Best Director" award for the object (such as a specific film, event, or year).
-
B.
winningFilmDirector
Indicates that the subject is the director of a film that has won a specified award or competition.
-
C.
bestAssistantDirectorWinnerFilm
Indicates that a film is the work for which a particular assistant director won the Best Assistant Director award.
-
D.
oscarCategoryWon
chosen
Indicates that an entity has won an Academy Award in the specified Oscar category.
-
E.
bestPictureWinner
Indicates that the subject is the film that won the Best Picture award in a given context or year.
- 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_69f224cb08908190ba71ad9aa87518ed |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f74062b9388190b30546cf700a825c |
completed | May 3, 2026, 12:32 p.m. |
| PD | Predicate disambiguation | batch_69f73c802b848190b61a416b7488bd96 |
completed | May 3, 2026, 12:16 p.m. |
Created at: April 29, 2026, 9 p.m.