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.