Triple

T26759808
Position Surface form Disambiguated ID Type / Status
Subject Adèle Varens E674768 entity
Predicate presumedRelationshipToRochester P94755 FINISHED
Object possible illegitimate daughter LITERAL 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: possible illegitimate daughter | Statement: [Adèle Varens, presumedRelationshipToRochester, possible illegitimate daughter]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: presumedRelationshipToRochester
Context triple: [Adèle Varens, presumedRelationshipToRochester, possible illegitimate daughter]
  • A. relationshipToBlancheDevereaux
    Indicates the specific type of personal or familial relationship an entity has with Blanche Devereaux.
  • B. relationshipToBaudelaires
    Indicates the type of personal or familial connection an entity has to the Baudelaires.
  • C. relationshipToRelative chosen
    Indicates the specific familial connection or kinship role that one person has in relation to a particular relative.
  • D. establishedRelationship
    Indicates that a formal, recognized relationship has been created and is now in effect between the referenced entities.
  • E. relationshipToAuntEller
    Indicates the specific familial relationship that an entity has to Aunt Eller (e.g., whether and how they are related to her).
  • F. None of above.

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_69eecda6e9dc81908452fab3ba17ed9b completed April 27, 2026, 2:44 a.m.
NER Named-entity recognition batch_69f618dafb6c8190b4f53a7fcbf967e3 completed May 2, 2026, 3:31 p.m.
PD Predicate disambiguation batch_69f60b8dfa0c8190864e1a940024d0a0 completed May 2, 2026, 2:34 p.m.
Created at: April 27, 2026, 3:57 a.m.