Triple

T3932775
Position Surface form Disambiguated ID Type / Status
Subject William Cohen E90832 entity
Predicate spouse P13 FINISHED
Object Janet Langhart E228216 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: Janet Langhart | Statement: [William Cohen, spouse, Janet Langhart]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Janet Langhart
Context triple: [William Cohen, spouse, Janet Langhart]
  • A. Janet Langhart chosen
    Janet Langhart is an American television journalist, author, and former model known for her work as a news correspondent and for her writings on race and civil rights.
  • B. Sandra Lee
    Sandra Lee is an American television chef and author known for her "Semi-Homemade" cooking concept and numerous Food Network shows.
  • C. Elizabeth Steward
    Elizabeth Steward was an English gentlewoman of the early 17th century best known as the mother of Oliver Cromwell, the future Lord Protector of England.
  • D. Christine Diane Teigen
    Christine Diane Teigen, known as Chrissy Teigen, is an American model, television personality, and cookbook author prominent for her Sports Illustrated work, social media presence, and lifestyle brand.
  • E. Paula Stewart
    Paula Stewart is an American actress and singer known for her work on Broadway and in television during the mid-20th century.
  • 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_69aed95f26e0819094b0e71974543a19 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aeedaaf3c881909539831bf3a8bf10 completed March 9, 2026, 3:56 p.m.
NED1 Entity disambiguation (via context triple) batch_69b52887d4a48190b51df3f51ff197c0 completed March 14, 2026, 9:21 a.m.
Created at: March 9, 2026, 3:23 p.m.