Triple

T19547192
Position Surface form Disambiguated ID Type / Status
Subject So Big (1953 film) E489103 entity
Predicate starring P1507 FINISHED
Object Richard Beymer 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: Richard Beymer | Statement: [So Big (1953 film), starring, Richard Beymer]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Richard Beymer
Context triple: [So Big (1953 film), starring, Richard Beymer]
  • A. Richard Beymer chosen
    Richard Beymer is an American actor best known for playing Tony in the 1961 film adaptation of the musical "West Side Story."
  • B. Julian Kaye
    Julian Kaye is a charismatic Los Angeles male escort whose luxurious lifestyle unravels when he becomes entangled in a murder investigation.
  • C. Eric Portman
    Eric Portman was a British stage and film actor known for his intense character roles in mid-20th-century cinema, particularly in wartime and thriller films.
  • D. Ormond Beatty
    Ormond Beatty was a 19th-century American educator and academic administrator best known for serving as president of Centre College in Kentucky.
  • E. Billy Hartnett
    Billy Hartnett is the commonly used name for William Hartnett, likely referring to him in informal or public contexts.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8e8db5b6c8190984b61f91981f575 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e63d2d8a6081908e9bb3a6f5d85896 completed April 20, 2026, 2:50 p.m.
Created at: April 10, 2026, 1:41 p.m.