Triple
T37398861
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Academy Award for Best Supporting Actress for Raging Bull |
E928934
|
entity |
| Predicate | subjectOfNominatedFilm |
P22751
|
FINISHED |
| Object | boxer Jake LaMotta |
—
|
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: boxer Jake LaMotta | Statement: [Academy Award for Best Supporting Actress for Raging Bull, subjectOfNominatedFilm, boxer Jake LaMotta]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: subjectOfNominatedFilm Context triple: [Academy Award for Best Supporting Actress for Raging Bull, subjectOfNominatedFilm, boxer Jake LaMotta]
-
A.
nominatedIn
Indicates that an entity has been formally put forward as a candidate for an award, position, or recognition within a specific event, context, or time period.
-
B.
subjectOfFilm
chosen
Indicates that a person, character, or topic is the main focus or central topic depicted in a particular film.
-
C.
associatedWithAwardNominatedFilm
Indicates that an entity has a relationship to a film that has been nominated for an award.
-
D.
nomineeOf
Indicates that one entity is a candidate put forward or selected for an award, position, or recognition by another entity.
-
E.
associatedAwardWinningFilm
Indicates that there is a relationship between an entity and a film with which it is connected, where that film has received an award.
- 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_69f76ebbf79c8190b85bbcf3a6be57e4 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fddd373cdc8190be1b12e70e4deb1f |
completed | May 8, 2026, 12:55 p.m. |
| PD | Predicate disambiguation | batch_69fddc6915a88190ad41e379aa3ede13 |
completed | May 8, 2026, 12:51 p.m. |
Created at: May 3, 2026, 4:16 p.m.