Triple

T20542695
Position Surface form Disambiguated ID Type / Status
Subject TFNG E504386 entity
Predicate member P10 FINISHED
Object Richard Truly 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: Richard Truly | Statement: [TFNG, member, Richard Truly]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Richard Truly
Context triple: [TFNG, member, Richard Truly]
  • A. Richard Truly chosen
    Richard Truly is a former U.S. Navy aviator, Space Shuttle astronaut, and later NASA Administrator who played a key role in the early Shuttle program and post-Challenger recovery.
  • B. Richard Seaton
    Richard Seaton is the brilliant scientist-hero of E.E. "Doc" Smith's Skylark space opera series, known for pioneering interstellar travel and battling cosmic threats.
  • C. Richard Robert
    Richard Robert was an influential piano teacher and musician best known for mentoring prominent 20th-century pianists such as Rudolf Serkin.
  • D. Richard Byard
    Richard Byard is a film editor known for his work on the crime thriller movie "Catch .44."
  • E. Christopher Edward Wilding
    Christopher Edward Wilding is a British-American film editor and producer, best known as one of the sons of legendary actress Elizabeth Taylor and actor Michael Wilding.
  • 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_69e0b4b476648190bc6019622ae54d3c completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6a293feac8190b27848b64f2db1fe completed April 20, 2026, 10:03 p.m.
Created at: April 16, 2026, 11:38 a.m.