Triple

T21660837
Position Surface form Disambiguated ID Type / Status
Subject James Harlan E534589 entity
Predicate name P16 FINISHED
Object James Harlan 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: James Harlan | Statement: [James Harlan, name, James Harlan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: James Harlan
Context triple: [James Harlan, name, James Harlan]
  • A. James Harlan chosen
    James Harlan was a 19th-century American politician from Iowa who served as a U.S. Senator and Secretary of the Interior under President Andrew Johnson.
  • B. Jan Harlan
    Jan Harlan is a film producer best known for his long-time collaboration with director Stanley Kubrick on several of his later films.
  • C. James S. Harlan
    James S. Harlan was an American lawyer and public official, known as the son of U.S. Supreme Court Justice John Marshall Harlan and for serving on the Interstate Commerce Commission.
  • D. Samuel S. Cox
    Samuel S. Cox was a prominent 19th-century American Democratic politician and U.S. Congressman known for his oratory and influential role in national politics during and after the Civil War.
  • E. Edwin G. Waite
    Edwin G. Waite was an American politician and public official known for serving as Secretary of State of California in the late 19th century.
  • 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_69e0c467e1f48190af2650b19175abc4 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ef6c07bcb88190a9864672c20325ff completed April 27, 2026, 2 p.m.
Created at: April 16, 2026, 6:36 p.m.