Triple

T19579564
Position Surface form Disambiguated ID Type / Status
Subject Denise Robert E489950 entity
Predicate notableWork P4 FINISHED
Object Aurore 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: Aurore | Statement: [Denise Robert, notableWork, Aurore]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Aurore
Context triple: [Denise Robert, notableWork, Aurore]
  • A. Aurore chosen
    Aurore is a French given name commonly used for women, derived from the Latin word for "dawn."
  • B. Heliane
    Heliane is the enigmatic and spiritually radiant heroine of Erich Wolfgang Korngold’s opera *Das Wunder der Heliane*, whose purity and inner conflict drive the work’s intense emotional drama.
  • C. Juliette
    Juliette is a feminine given name of French origin, widely used in many countries and popularized through literature and film.
  • D. Edmée
    Edmée is a feminine given name of French origin, often considered a variant of Edmé and historically associated with French-speaking regions.
  • E. Delphine
    Delphine is an epistolary novel by Madame de Staël that explores themes of love, social convention, and women's independence in late 18th-century French society.
  • 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_69d8e8dd9374819098e36349b3211663 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e6402763b8819099e535979f094f9d completed April 20, 2026, 3:03 p.m.
Created at: April 10, 2026, 1:42 p.m.