Triple

T20663701
Position Surface form Disambiguated ID Type / Status
Subject Tony Hillerman E507825 entity
Predicate mainCharacter P1183 FINISHED
Object Joe Leaphorn 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: Joe Leaphorn | Statement: [Tony Hillerman, mainCharacter, Joe Leaphorn]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Joe Leaphorn
Context triple: [Tony Hillerman, mainCharacter, Joe Leaphorn]
  • A. Joe Leaphorn in Dark Winds chosen
    Joe Leaphorn in Dark Winds is a seasoned Navajo Tribal Police lieutenant whose methodical investigations intertwine crime-solving with Navajo culture and spiritual beliefs in the 1970s Southwest.
  • B. Walt Longmire
    Walt Longmire is a fictional, laconic Wyoming sheriff known for his strong moral code and central role in Craig Johnson’s mystery novels and their television adaptation.
  • C. Wilbur Longmire
    Wilbur Longmire is a musician and songwriter best known for his work in jazz and soul music.
  • D. Matt Houston
    Matt Houston is an American television crime drama series from the 1980s centered on a wealthy Texas private investigator in Los Angeles.
  • E. Harry Block
    Harry Block is the neurotic, self-absorbed writer protagonist of Woody Allen’s film "Deconstructing Harry," whose chaotic personal life fuels his fiction.
  • 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_69e0b4c059bc81908ea762cd73ea4424 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6b2f4872481908858eb88ce89dd47 completed April 20, 2026, 11:12 p.m.
Created at: April 16, 2026, 11:44 a.m.