Triple

T22090122
Position Surface form Disambiguated ID Type / Status
Subject Shootout at Candyland E545890 entity
Predicate antagonist P4675 FINISHED
Object Calvin Candie 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: Calvin Candie | Statement: [Shootout at Candyland, antagonist, Calvin Candie]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Calvin Candie
Context triple: [Shootout at Candyland, antagonist, Calvin Candie]
  • A. Calvin Candie chosen
    Calvin Candie is a sadistic and flamboyant Southern plantation owner who serves as the main antagonist in Quentin Tarantino's film "Django Unchained."
  • B. Countee LeRoy Porter
    Countee LeRoy Porter, better known as Countee Cullen, was a prominent American poet and leading figure of the Harlem Renaissance.
  • C. William Devaynes
    William Devaynes was a British politician and merchant active in the late 18th century, known for his involvement in imperial and commercial ventures.
  • D. Clarence Boddicker
    Clarence Boddicker is the sadistic crime boss and primary human antagonist in the 1987 science fiction action film "RoboCop."
  • E. Cecil Gaines
    Cecil Gaines is the fictionalized African-American White House butler whose life story, spanning decades of service to multiple U.S. presidents, is portrayed in the film "The Butler."
  • 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_69f128e53dfc81909858cdad8b09c5fb completed April 28, 2026, 9:38 p.m.
Created at: April 16, 2026, 8:29 p.m.