Triple

T10509612
Position Surface form Disambiguated ID Type / Status
Subject Jill Biden E247876 entity
Predicate spouse P13 FINISHED
Object Bill Stevenson E247876 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: Bill Stevenson | Statement: [Jill Biden, spouse, Bill Stevenson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bill Stevenson
Context triple: [Jill Biden, spouse, Bill Stevenson]
  • A. Bill Stevenson chosen
    Bill Stevenson is an American businessman best known as the first husband of Jill Biden, the current First Lady of the United States.
  • B. Bill Steele
    Bill Steele is a Canadian municipal politician who serves as the mayor of Port Colborne, Ontario.
  • C. Bill McBride
    Bill McBride was a Florida lawyer and Democratic politician best known for being the party’s nominee for governor in the 2002 Florida gubernatorial election against incumbent Jeb Bush.
  • D. Kevin Garvey
    Kevin Garvey is the troubled small-town police chief and central protagonist of the television drama "The Leftovers," known for his psychological struggles amid a mysteriously altered world.
  • E. Bill Tierney
    Bill Tierney is a Hall of Fame American lacrosse coach renowned for leading multiple NCAA championship teams, most notably at Princeton and later at the University of Denver.
  • 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_69d381c4aa948190942e1d803143fb0e completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d509b359ac8190b3683cc6b9c70a71 completed April 7, 2026, 1:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69d95e5d1a2c81908a9bb8f1c55414fa completed April 10, 2026, 8:32 p.m.
Created at: April 6, 2026, 12:27 p.m.