Triple

T5762078
Position Surface form Disambiguated ID Type / Status
Subject This Week E127118 entity
Predicate presenter P83 FINISHED
Object David Brinkley E84909 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: David Brinkley | Statement: [This Week, presenter, David Brinkley]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: David Brinkley
Context triple: [This Week, presenter, David Brinkley]
  • A. David Brinkley chosen
    David Brinkley was a prominent American television newscaster and journalist best known for co-anchoring "The Huntley–Brinkley Report" and later serving as a leading figure in network evening news.
  • B. Bill Whitaker
    Bill Whitaker is an American television journalist best known as a longtime correspondent for the CBS news magazine program "60 Minutes."
  • C. Peter Jennings
    Peter Jennings was a prominent Canadian-American journalist best known as the longtime anchor of ABC’s flagship evening news program, World News Tonight.
  • D. Dan Rather
    Dan Rather is an American journalist and former CBS Evening News anchor known for his hard-hitting reporting and decades-long presence on national television news.
  • E. Mike Wallace
    Mike Wallace was a prominent American broadcast journalist best known as a hard-hitting correspondent on the television news magazine "60 Minutes."
  • 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_69c00833a3fc81908f4bc29ed011b7a6 completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c02939b22c81908f8354ab175d168d completed March 22, 2026, 5:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69c07e5547f88190b950a3037708f820 completed March 22, 2026, 11:42 p.m.
Created at: March 22, 2026, 3:49 p.m.