Triple

T15080600
Position Surface form Disambiguated ID Type / Status
Subject Steve King E380129 entity
Predicate name P16 FINISHED
Object Steve King E380129 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: Steve King | Statement: [Steve King, name, Steve King]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Steve King
Context triple: [Steve King, name, Steve King]
  • A. Steve King chosen
    Steve King is a former Republican U.S. Representative from Iowa known for his hardline conservative positions and controversial remarks on immigration and race.
  • B. Stephen King
    Stephen King is a prolific American author renowned for his horror, supernatural fiction, suspense, and fantasy novels, many of which have been adapted into successful films and television series.
  • C. Dean Koontz
    Dean Koontz is a bestselling American author known for his suspenseful thrillers that blend horror, mystery, and science fiction elements.
  • D. Jonathan Rollins
    Jonathan Rollins is a high-powered, ambitious attorney on the television series "L.A. Law," known for his sharp legal skills and complex personal relationships.
  • E. David Koontz
    David Koontz is known as the husband of author and actress Christina Crawford, who wrote the memoir "Mommie Dearest."
  • 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_69d85cd7683881908d405c1b5d7b4f7f completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69dff80008c88190840f94222f867478 completed April 15, 2026, 8:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69feae15d6308190a62b4f66c550db04 completed May 9, 2026, 3:46 a.m.
Created at: April 10, 2026, 3:03 a.m.