Triple

T5713921
Position Surface form Disambiguated ID Type / Status
Subject Heaven Can Wait E125976 entity
Predicate screenwriter P2831 FINISHED
Object Elaine May E253251 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: Elaine May | Statement: [Heaven Can Wait, screenwriter, Elaine May]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Elaine May
Context triple: [Heaven Can Wait, screenwriter, Elaine May]
  • A. Elaine May chosen
    Elaine May is an American comedian, writer, director, and actress, renowned as a pioneer of improvisational comedy and for her influential work in film and theater.
  • B. Caroline Reitman
    Caroline Reitman is a member of the Reitman family, known as the daughter of late filmmaker and producer Ivan Reitman.
  • C. Priscilla Lane
    Priscilla Lane was an American film actress best known as one of the Lane Sisters and for her roles in popular 1930s and 1940s Hollywood films.
  • D. Marshall Brickman
    Marshall Brickman is an American screenwriter, director, and former television writer best known for co-writing several acclaimed Woody Allen films, including "Annie Hall" and "Manhattan."
  • E. Rita Rudner
    Rita Rudner is an American stand-up comedian, actress, and author known for her dry, understated wit and numerous television and stage appearances.
  • 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_69c0082d6fe48190b777fb383769e5c8 completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c024b5205c8190aaab291a6e485ec1 completed March 22, 2026, 5:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69c05a74b350819099d8881ef248e1e7 completed March 22, 2026, 9:09 p.m.
Created at: March 22, 2026, 3:46 p.m.