Triple

T22312503
Position Surface form Disambiguated ID Type / Status
Subject Lev Sedov E551553 entity
Predicate spouse P13 FINISHED
Object Jeanne Martin 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: Jeanne Martin | Statement: [Lev Sedov, spouse, Jeanne Martin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jeanne Martin
Context triple: [Lev Sedov, spouse, Jeanne Martin]
  • A. Jeanne Martin chosen
    Jeanne Martin was the wife of Lev Sedov, the revolutionary son of Russian Marxist leader Leon Trotsky.
  • B. Jeanne Olivier
    Jeanne Olivier is known as the former spouse of American actor and author Christopher Lawford, a member of the Kennedy family.
  • C. Jeanne Biegger
    Jeanne Biegger was an American model and socialite best known as the second wife of entertainer Dean Martin, with whom she shared a highly publicized mid-20th-century Hollywood marriage.
  • D. Jeanne Rucar
    Jeanne Rucar was a French-born gymnast and memoirist best known as the longtime wife and confidante of Spanish filmmaker Luis Buñuel.
  • E. Jeanne Molbech
    Jeanne Molbech was the Danish-born wife and close intellectual companion of French writer Léon Bloy, known for supporting and influencing his literary and spiritual life.
  • 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_69e11e4776588190abb21e5cea79973f completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f1574f97cc81909685aeef15d02af9 completed April 29, 2026, 12:56 a.m.
Created at: April 16, 2026, 8:42 p.m.