Triple

T19843818
Position Surface form Disambiguated ID Type / Status
Subject Julie Clary E476804 entity
Predicate birthName P65 FINISHED
Object Marie Julie Clary 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: Marie Julie Clary | Statement: [Julie Clary, birthName, Marie Julie Clary]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marie Julie Clary
Context triple: [Julie Clary, birthName, Marie Julie Clary]
  • A. Marie Julie Clary chosen
    Marie Julie Clary was a Frenchwoman who became Queen consort of Naples and later of Spain as the wife of Joseph Bonaparte, Napoleon Bonaparte’s elder brother.
  • B. Louise Dupin
    Louise Dupin was an 18th-century French salonnière, intellectual, and early feminist thinker known for hosting prominent Enlightenment figures and advocating for women's rights.
  • C. Mathilde Bonnefoy
    Mathilde Bonnefoy is a German film editor and producer best known for her work on acclaimed documentaries and feature films, including the Oscar-winning "Citizenfour."
  • D. Anne Jules de Noailles
    Anne Jules de Noailles was a prominent French nobleman and military commander who served as a marshal of France under Louis XIV.
  • E. Agathe de La Boulaye
    Agathe de La Boulaye is a French actress known for her roles in international films and television, including the science-fiction horror movie "Alien vs. Predator."
  • 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_69d8e51d39d081909bcfafeaaf3d2fcc completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e658085a148190a305bde0897dfe84 completed April 20, 2026, 4:44 p.m.
Created at: April 10, 2026, 1:51 p.m.