Triple

T3239270
Position Surface form Disambiguated ID Type / Status
Subject The Cosby Show E67928 entity
Predicate starring P1507 FINISHED
Object Lisa Bonet E185413 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: Lisa Bonet | Statement: [The Cosby Show, starring, Lisa Bonet]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lisa Bonet
Context triple: [The Cosby Show, starring, Lisa Bonet]
  • A. Lisa Bonet chosen
    Lisa Bonet is an American actress best known for her role as Denise Huxtable on "The Cosby Show" and its spin-off "A Different World."
  • B. Janeane Garofalo
    Janeane Garofalo is an American stand-up comedian, actress, and political activist known for her sharp, sardonic wit and roles in films like "Reality Bites" and "The Truth About Cats & Dogs."
  • C. Jill Hennessy
    Jill Hennessy is a Canadian actress and musician best known for her leading roles on the television series Law & Order and Crossing Jordan.
  • D. Kirstie Alley
    Kirstie Alley was an American actress best known for her Emmy-winning role as Rebecca Howe on the hit sitcom "Cheers" and for her work in films like "Look Who's Talking."
  • E. Shelley Long
    Shelley Long is an American actress best known for her Emmy-winning role as Diane Chambers on the television sitcom "Cheers."
  • 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_69ad858d27348190abb61c280b4c86a9 completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69adaef4c0bc819095e4f84296fe7cb6 completed March 8, 2026, 5:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69b28eadeff481909bd48cdf51044f86 completed March 12, 2026, 10 a.m.
Created at: March 8, 2026, 3:08 p.m.