Triple

T2576280
Position Surface form Disambiguated ID Type / Status
Subject Michael Mann E57782 entity
Predicate directed P7373 FINISHED
Object Heat E174842 NE FINISHED

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: Heat | Statement: [Michael Mann, directed, Heat]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Heat
Context triple: [Michael Mann, directed, Heat]
  • A. Heat chosen
    Heat is a 1995 crime thriller film directed by Michael Mann, renowned for its intense heist sequences and the iconic pairing of Al Pacino and Robert De Niro.
  • B. Thermal
    Thermal is an unincorporated community in California’s Coachella Valley, known for its desert climate and proximity to agricultural and resort areas.
  • C. Heat Wave
    "Heat Wave" is a popular rock and pop cover song performed by Linda Ronstadt, known for its energetic vocals and success on the charts in the mid-1970s.
  • D. High Heat
    High Heat is a Major League Baseball talk show on MLB Network featuring lively analysis, debate, and commentary on current baseball news and issues.
  • E. Body Heat
    Body Heat is a 1981 neo-noir erotic thriller film, written and directed by Lawrence Kasdan, about a small-town lawyer drawn into a deadly affair and murder plot.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69ab4a51410081908501dcf8bad9adc4 completed March 6, 2026, 9:42 p.m.
NER Named-entity recognition batch_69abd3a606e481909bcea46de468bb99 completed March 7, 2026, 7:28 a.m.
NED1 Entity disambiguation (via context triple) batch_69af83aefb00819095a6ab26f9bb61d9 completed March 10, 2026, 2:36 a.m.
Created at: March 6, 2026, 9:49 p.m.