Triple

T18229543
Position Surface form Disambiguated ID Type / Status
Subject Judith Steinberg Dean E436507 entity
Predicate spouse P13 FINISHED
Object Howard Dean 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: Howard Dean | Statement: [Judith Steinberg Dean, spouse, Howard Dean]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Howard Dean
Context triple: [Judith Steinberg Dean, spouse, Howard Dean]
  • A. Howard Dean chosen
    Howard Dean is an American physician and politician who served as governor of Vermont and later became a prominent Democratic National Committee chairman and early advocate of internet-based political campaigning.
  • B. John Edwards
    John Edwards is a New Zealand lawyer and privacy expert who serves as the United Kingdom’s Information Commissioner, overseeing data protection and information rights.
  • C. John Edwards
    John Edwards is a musician known for his work as a member of the band The Stooges.
  • D. John Edwards
    John Edwards is an American lawyer and former U.S. senator from North Carolina who was the Democratic vice-presidential nominee in the 2004 election.
  • E. John Edwards
    John Edwards was an American statesman who represented South Carolina in the Continental Congress during the Revolutionary era.
  • 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_69d8b9103a8081908bbb0836fef10efd completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4f4b1b2108190a5585bbfaf2d295b completed April 19, 2026, 3:28 p.m.
Created at: April 10, 2026, 10:33 a.m.