Triple

T9971787
Position Surface form Disambiguated ID Type / Status
Subject Sarah Bernhardt E196223 entity
Predicate familyName P18 FINISHED
Object Bernhardt E196223 NE 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: Bernhardt | Statement: [Sarah Bernhardt, familyName, Bernhardt]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bernhardt
Context triple: [Sarah Bernhardt, familyName, Bernhardt]
  • A. Bernhardt chosen
    Bernhardt is a German-origin surname and given name, most famously associated with the legendary French stage actress Sarah Bernhardt.
  • B. Renée Adorée
    Renée Adorée was a French-born silent film actress best known for her acclaimed role in the World War I drama "The Big Parade" (1925).
  • C. Madame Arcati
    Madame Arcati is the eccentric, enthusiastic medium from Noël Coward’s play "Blithe Spirit," best known in popular culture through Margaret Rutherford’s comic film portrayal.
  • D. Brigitte
    Brigitte is a French former teacher best known as the wife of Emmanuel Macron, the President of France.
  • E. Odile
    Odile is the seductive and deceptive Black Swan character in the ballet "Swan Lake," often portrayed as the antagonist and foil to the virtuous Odette.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69ca82eea2b88190a0e511d21a31f386 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cdb7bb03688190a3f4fc1988b8fafa completed April 2, 2026, 12:26 a.m.
NED1 Entity disambiguation (via context triple) batch_69d23dd3e47c819095fef68b9939ec19 completed April 5, 2026, 10:47 a.m.
Created at: March 30, 2026, 8:48 p.m.