Triple

T22601253
Position Surface form Disambiguated ID Type / Status
Subject Janet Devereaux E574823 entity
Predicate hasMother P1909 FINISHED
Object Blanche Devereaux 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: Blanche Devereaux | Statement: [Janet Devereaux, hasMother, Blanche Devereaux]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Blanche Devereaux
Context triple: [Janet Devereaux, hasMother, Blanche Devereaux]
  • A. Blanche Devereaux chosen
    Blanche Devereaux is a flirtatious, glamorous Southern belle and one of the four central housemates in the classic sitcom "The Golden Girls."
  • B. Blanche Amory
    Blanche Amory is a flirtatious, manipulative young woman in William Makepeace Thackeray’s novel "Pendennis," known for her coquetry and ambition in Victorian society.
  • C. Blanche DuBois
    Blanche DuBois is the fragile, delusional Southern belle at the center of Tennessee Williams' play "A Streetcar Named Desire," whose psychological unraveling drives the story's tragic arc.
  • D. Blanche
    Blanche is a Paris Métro station located in the Montmartre area, serving Line 2 near the Moulin Rouge.
  • E. Blanche
    Blanche is a feminine given name of French origin historically associated with nobility and literary figures.
  • 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_69e245bc11308190b69d794d5d1e0bb6 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1626db69481908ec9f9c7d320d3cb completed April 29, 2026, 1:44 a.m.
Created at: April 17, 2026, 2:50 p.m.