Triple

T19647893
Position Surface form Disambiguated ID Type / Status
Subject Gifted E471728 entity
Predicate producer P490 FINISHED
Object Andy Cohen 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: Andy Cohen | Statement: [Gifted, producer, Andy Cohen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Andy Cohen
Context triple: [Gifted, producer, Andy Cohen]
  • A. Andy Cohen chosen
    Andy Cohen is an American television host, producer, and author best known for hosting Bravo’s late-night talk show "Watch What Happens Live" and executive producing the "Real Housewives" franchise.
  • B. Jerry Morgan
    Jerry Morgan is a central comedic character portrayed by Danny Kaye in the 1954 musical comedy film "Knock on Wood."
  • C. Robert Cohl
    Robert Cohl is the son of Canadian film producer and Toronto International Film Festival co-founder Dusty Cohl.
  • D. David Aaron Cohen
    David Aaron Cohen is an American screenwriter best known for co-writing the sports drama film "Friday Night Lights."
  • E. Kevin Kimmel
    Kevin Kimmel is an American actor and voice actor best known for his work on animated series and for being the son of television host Jimmy Kimmel.
  • 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_69d8e51395348190ac1416d46dfc6db0 completed April 10, 2026, 11:54 a.m.
NER Named-entity recognition batch_69e64126cea88190a1a6929f46de4686 completed April 20, 2026, 3:07 p.m.
Created at: April 10, 2026, 1:44 p.m.