Triple

T22092513
Position Surface form Disambiguated ID Type / Status
Subject Grease Live E545944 entity
Predicate stars P1956 FINISHED
Object Didi Conn 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: Didi Conn | Statement: [Grease Live, stars, Didi Conn]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Didi Conn
Context triple: [Grease Live, stars, Didi Conn]
  • A. Didi Conn chosen
    Didi Conn is an American actress best known for her role as the bubbly, high-voiced Frenchy in the classic film musical "Grease."
  • B. Nina Pedrad
    Nina Pedrad is a television writer and producer known for her work on series such as the mystery-comedy show "Poker Face."
  • C. Abigail Phillips
    Abigail Phillips was the birth name of Abigail Phillips Quincy, a 19th-century American woman associated with the prominent Quincy family of Massachusetts.
  • D. Georgia Engel
    Georgia Engel was an American actress best known for her soft-spoken, sweetly quirky roles in television comedies such as "The Mary Tyler Moore Show" and "Everybody Loves Raymond."
  • E. Alicia Witt
    Alicia Witt is an American actress, singer-songwriter, and pianist known for her roles in film and television, including appearances in projects like "Mr. Holland's Opus," "Dune," and "The Walking Dead."
  • 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_69e11e36d03c8190a83a1ba802b7231b completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f128e6b1d881909bf0f4a52199354c completed April 28, 2026, 9:38 p.m.
Created at: April 16, 2026, 8:29 p.m.