Triple

T16889210
Position Surface form Disambiguated ID Type / Status
Subject André David E421620 entity
Predicate name P16 FINISHED
Object André David 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: André David | Statement: [André David, name, André David]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: André David
Context triple: [André David, name, André David]
  • A. André David chosen
    André David was one of the discoverers of the prehistoric painted cave of Pech Merle in southwestern France.
  • B. André Daina
    André Daina is a Swiss former football referee best known for officiating major European club competitions in the 1980s.
  • C. André Pierre
    André Pierre was a renowned Haitian painter celebrated as one of the leading figures of Haitian naïve art, known especially for his vibrant, spiritually themed works.
  • D. André Daven
    André Daven was a French film producer and occasional director active in the early 20th century, known for his work in European cinema during the 1930s.
  • E. André Dewavrin
    André Dewavrin was a French military officer and intelligence leader best known for organizing and directing Free French secret services and resistance operations during World War II.
  • 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_69d889d470fc8190b4aec199636c0c56 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e3bbc3b5188190ac713b4d4166e961 completed April 18, 2026, 5:13 p.m.
Created at: April 10, 2026, 5:29 a.m.