Triple

T21607915
Position Surface form Disambiguated ID Type / Status
Subject Gino Severini E533224 entity
Predicate spouse P13 FINISHED
Object Jeanne Fort 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 Fort | Statement: [Gino Severini, spouse, Jeanne Fort]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jeanne Fort
Context triple: [Gino Severini, spouse, Jeanne Fort]
  • A. Jeanne Fort chosen
    Jeanne Fort was the wife of Italian Futurist painter Gino Severini and a figure connected to the early 20th-century Parisian art world.
  • B. Jeanne Bal
    Jeanne Bal was an American actress best known for her television work in the 1950s and 1960s, including appearances on series such as Star Trek and Perry Mason.
  • C. Jeanette Bonnier
    Jeanette Bonnier was a Swedish publisher, art patron, and media executive, known for her influential role in the Bonnier media empire and her contributions to contemporary art.
  • D. Jeanette Demont
    Jeanette Demont was the first wife of American oil tycoon and art collector J. Paul Getty.
  • E. Jeanne Campbell
    Jeanne Campbell was a British socialite and journalist known for her connections to prominent literary and political figures, including her marriage to American novelist Norman Mailer.
  • 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_69e0c46411108190bba0d4176dffc9f3 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ef17e6378881908678dc903b8ba6ac completed April 27, 2026, 8:01 a.m.
Created at: April 16, 2026, 6:33 p.m.