Triple

T16013575
Position Surface form Disambiguated ID Type / Status
Subject Lori Martin E388402 entity
Predicate coStarredWith P14987 FINISHED
Object Polly Bergen E289333 NE 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: Polly Bergen | Statement: [Lori Martin, coStarredWith, Polly Bergen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Polly Bergen
Context triple: [Lori Martin, coStarredWith, Polly Bergen]
  • A. Polly Bergen chosen
    Polly Bergen was an American actress and singer known for her work in film, television, and theater, including a prominent role in the 1962 thriller "Cape Fear."
  • B. Carol Rossen
    Carol Rossen is an American actress best known for her supporting roles in films and television during the 1960s and 1970s.
  • C. Estelle Parsons
    Estelle Parsons is an American actress and director best known for her Academy Award–winning performance in the 1967 film "Bonnie and Clyde" and her extensive work on stage and television.
  • D. Ruth Gordon
    Ruth Gordon was an American actress and screenwriter renowned for her late-career film roles, particularly in "Rosemary's Baby" and "Harold and Maude."
  • E. Julie Harris
    Julie Harris was an acclaimed British costume designer known for her work on numerous films, including the Academy Award-winning costumes for "Darling."
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69d86dabcb7c8190b6a39d6831d2fa1b completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e18292b79881908efac869603c4029 completed April 17, 2026, 12:45 a.m.
NED1 Entity disambiguation (via context triple) batch_6a00aae0f87c819085ebc7d475ebe8ba completed May 10, 2026, 3:57 p.m.
Created at: April 10, 2026, 4:55 a.m.