Triple

T20417099
Position Surface form Disambiguated ID Type / Status
Subject Midnight in the Garden of Good and Evil E500740 entity
Predicate castMember P1668 FINISHED
Object John Cusack 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: John Cusack | Statement: [Midnight in the Garden of Good and Evil, castMember, John Cusack]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Cusack
Context triple: [Midnight in the Garden of Good and Evil, castMember, John Cusack]
  • A. John Cusack chosen
    John Cusack is an American actor, screenwriter, and producer known for his roles in films like "Say Anything..." and "High Fidelity" and for his outspoken political activism.
  • B. John C. Reilly
    John C. Reilly is an American actor known for his versatile performances in both dramatic films and broad comedies, including roles in movies like "Chicago," "Boogie Nights," and "Step Brothers."
  • C. Paul Cusack
    Paul Cusack is one of the children of renowned Irish actor Cyril Cusack, belonging to a prominent family in theatre and film.
  • D. John R. Reilly
    John R. Reilly was an American actor known for his role in the World War II film "The Story of G.I. Joe."
  • E. Rob Lowe
    Rob Lowe is an American actor known for his roles in films like "St. Elmo's Fire" and TV series such as "Parks and Recreation" and "9-1-1: Lone Star."
  • 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_69e0b4a935588190b9446a99b37ced44 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e67a4437448190b07b6e6e3de5830f completed April 20, 2026, 7:11 p.m.
Created at: April 16, 2026, 11:30 a.m.