Triple

T17865530
Position Surface form Disambiguated ID Type / Status
Subject The Maze E446688 entity
Predicate producer P490 FINISHED
Object Richard Heermance 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: Richard Heermance | Statement: [The Maze, producer, Richard Heermance]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Richard Heermance
Context triple: [The Maze, producer, Richard Heermance]
  • A. Richard Heermance chosen
    Richard Heermance was an American film producer and editor active in mid-20th-century cinema.
  • B. Robert Hohman
    Robert Hohman is an American entrepreneur best known as the co-founder and former CEO of Glassdoor, a popular platform for anonymous employee reviews and salary information.
  • C. James Hartman
    James Hartman is an editor known for his work on the Cambridge Encyclopedia of the English Language and related linguistic reference works.
  • D. Gary Hinman
    Gary Hinman was an American music teacher and PhD student whose 1969 killing by associates of Charles Manson is considered one of the first Manson Family murders.
  • E. Robert Emhardt
    Robert Emhardt was an American character actor known for his numerous supporting roles in mid-20th-century film and television, often portraying villains or authority figures.
  • 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_69d8b9f4c22c819093c2680434472894 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e49793a2588190bb341ac606d767fe completed April 19, 2026, 8:51 a.m.
Created at: April 10, 2026, 10:17 a.m.