Triple

T20135918
Position Surface form Disambiguated ID Type / Status
Subject Black or White (2014 film) E491024 entity
Predicate starring P1507 FINISHED
Object Kevin Costner 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: Kevin Costner | Statement: [Black or White (2014 film), starring, Kevin Costner]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kevin Costner
Context triple: [Black or White (2014 film), starring, Kevin Costner]
  • A. Kevin Costner chosen
    Kevin Costner is an American actor and filmmaker known for leading roles in films such as "Dances with Wolves," "Field of Dreams," and "The Bodyguard."
  • B. Joe Costner
    Joe Costner is an American actor and the son of Academy Award–winning actor and filmmaker Kevin Costner.
  • C. Liam Costner
    Liam Costner is one of Kevin Costner’s children, known primarily for his connection to the famous American actor and filmmaker.
  • D. Hayes Costner
    Hayes Costner is a person known primarily as a sibling of Cayden Costner.
  • E. Craig Nelson
    Craig Nelson is an actor known for his role in the 1973 blaxploitation horror film "Scream Blacula Scream."
  • 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_69da62651a0c8190a3e05e95e056a66b completed April 11, 2026, 3:01 p.m.
NER Named-entity recognition batch_69e66767ba3881909c2bcb74a986bd29 completed April 20, 2026, 5:50 p.m.
Created at: April 11, 2026, 11:32 p.m.