Triple

T20908342
Position Surface form Disambiguated ID Type / Status
Subject Inferno (short film) E514866 entity
Predicate creator P184 FINISHED
Object Mike Hill 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: Mike Hill | Statement: [Inferno (short film), creator, Mike Hill]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mike Hill
Context triple: [Inferno (short film), creator, Mike Hill]
  • A. Mike Hill chosen
    Mike Hill is a filmmaker best known for directing the short film "Inferno."
  • B. Mike Hill
    Mike Hill was an American film editor best known for his long-time collaboration with director Ron Howard on acclaimed films such as "A Beautiful Mind."
  • C. Mike Hill
    Mike Hill is a collegiate sports administrator who serves as the athletic director for the University of North Carolina at Charlotte’s Charlotte 49ers athletic program.
  • D. Tim Hill
    Tim Hill is an American politician who served as the King County Executive in Washington State.
  • E. Tim Hill
    Tim Hill is an American film director and screenwriter best known for family-oriented live-action and animated movies such as "Hop," "Alvin and the Chipmunks," and "The SpongeBob SquarePants Movie."
  • 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_69e0b4f8a1108190bce3d31331290ced completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6e901ca50819080b123af7977efbd completed April 21, 2026, 3:03 a.m.
Created at: April 16, 2026, 12:48 p.m.