Triple

T20734065
Position Surface form Disambiguated ID Type / Status
Subject Stephen Herek E509644 entity
Predicate directorOf P537 FINISHED
Object Holy Man 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: Holy Man | Statement: [Stephen Herek, directorOf, Holy Man]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Holy Man
Context triple: [Stephen Herek, directorOf, Holy Man]
  • A. Holy Man chosen
    Holy Man is a 1998 American comedy film starring Eddie Murphy as a mysterious spiritual guru who becomes an unlikely television sensation.
  • B. Heartman
    Heartman is a key character in the video game "Death Stranding," a member of the Bridges organization who repeatedly dies and is revived in cycles while searching for his family on the Beach.
  • C. God’s Man
    God’s Man is a 1929 wordless novel by American artist Lynd Ward, renowned for its powerful woodcut illustrations that explore themes of ambition, art, and fate.
  • D. Merely a Man
    Merely a Man is a song featured on the album "Oranges & Lemons" by the English rock band XTC.
  • E. Ordinary Man
    "Ordinary Man" is a song by British singer-songwriter Mika from his album "No Place in Heaven."
  • 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_69e0b4c589c08190834fb5d86d0efa2b completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c1ef3040819085c8056e75571104 completed April 21, 2026, 12:16 a.m.
Created at: April 16, 2026, 12:31 p.m.