Triple

T8142452
Position Surface form Disambiguated ID Type / Status
Subject Le Déjeuner des canotiers E190128 entity
Predicate depictsPerson P1852 FINISHED
Object Ellen Andrée E295066 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: Ellen Andrée | Statement: [Le Déjeuner des canotiers, depictsPerson, Ellen Andrée]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ellen Andrée
Context triple: [Le Déjeuner des canotiers, depictsPerson, Ellen Andrée]
  • A. Ellen Andrée chosen
    Ellen Andrée was a French actress and artists’ model of the late 19th century, known for posing for prominent Impressionist painters such as Edgar Degas and Édouard Manet.
  • B. Marie Selland
    Marie Selland was the first wife of American film director Sam Peckinpah, known primarily in relation to his early personal life.
  • C. Marie Andersen
    Marie Andersen was the wife of Norwegian Nobel Prize–winning author Knut Hamsun and a significant figure in his personal and literary life.
  • D. Margarete Jensen
    Margarete Jensen was the wife of German nuclear physicist and Nobel laureate Hans D. Jensen.
  • E. Hermine Andermann
    Hermine Andermann was the mother of Austrian-American mathematician Karl Menger.
  • 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_69ca82bd9900819099477cdc2eb4244f completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb4443a3748190bbae79f1d673c03d completed March 31, 2026, 3:49 a.m.
NED1 Entity disambiguation (via context triple) batch_69cc94a9ecd08190a029a8d76d9f3bb1 completed April 1, 2026, 3:44 a.m.
Created at: March 30, 2026, 5:36 p.m.