Triple
T28656311
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Academy Award for Best Supporting Actress (won by Ruth Gordon) |
E725343
|
entity |
| Predicate | winnerFilmGenre |
P93695
|
FINISHED |
| Object | horror film |
—
|
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: horror film | Statement: [Academy Award for Best Supporting Actress (won by Ruth Gordon), winnerFilmGenre, horror film]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: winnerFilmGenre Context triple: [Academy Award for Best Supporting Actress (won by Ruth Gordon), winnerFilmGenre, horror film]
-
A.
keyGenreFilm
Indicates that a particular genre is the primary or defining genre associated with a given film.
-
B.
sourceFilmGenre
chosen
Indicates that a film is classified as belonging to a particular genre.
-
C.
distributedFilmGenre
Indicates that an entity (such as a company or distributor) distributed a film belonging to a particular genre.
-
D.
awardGenreFocus
Indicates that an award specifically recognizes or emphasizes works within a particular genre.
-
E.
visualGenre
Indicates the visual or stylistic category to which something belongs, such as its artistic or cinematic genre.
- 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_69f01d84f5f0819087ab5e6143b14ed7 |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_69f6afebd7ec8190ab696f363d84abf0 |
completed | May 3, 2026, 2:16 a.m. |
| PD | Predicate disambiguation | batch_69f6aca204148190850a3dc325bc07b7 |
completed | May 3, 2026, 2:02 a.m. |
Created at: April 28, 2026, 4:55 a.m.