Triple

T19899992
Position Surface form Disambiguated ID Type / Status
Subject John Hough E478257 entity
Predicate notableWork P4 FINISHED
Object Dirty Mary, Crazy Larry 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: Dirty Mary, Crazy Larry | Statement: [John Hough, notableWork, Dirty Mary, Crazy Larry]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dirty Mary, Crazy Larry
Context triple: [John Hough, notableWork, Dirty Mary, Crazy Larry]
  • A. Dirty Mary, Crazy Larry chosen
    Dirty Mary, Crazy Larry is a 1974 American action film known for its high-speed car chases and stars Peter Fonda as part of a criminal duo on the run.
  • B. The Lady Killer
    The Lady Killer is CeeLo Green’s critically acclaimed 2010 soul and R&B album best known for the hit single "Forget You."
  • C. Lady Killer
    Lady Killer is a 1933 American pre-Code crime-comedy film starring James Cagney as a small-time crook who becomes a Hollywood star.
  • D. Along Comes Mary
    "Along Comes Mary" is a song recorded by the American alternative rock band Bloodhound Gang, known for their irreverent, humorous style.
  • E. The Happy Hooker
    The Happy Hooker is a 1975 comedy film based on Xaviera Hollander’s memoir, in which Lynn Redgrave stars as a high-class call girl navigating the sex industry with humor and independence.
  • 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_69d8e520682081909892916424699bd5 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65940cf8c8190b74e51635410e48a completed April 20, 2026, 4:50 p.m.
Created at: April 10, 2026, 1:52 p.m.