Triple

T6499644
Position Surface form Disambiguated ID Type / Status
Subject André Marty E148851 entity
Predicate name P16 FINISHED
Object André Marty E148851 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: André Marty | Statement: [André Marty, name, André Marty]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: André Marty
Context triple: [André Marty, name, André Marty]
  • A. André Marty chosen
    André Marty was a French communist politician and militant who became infamous for his leadership role and harsh disciplinary actions within the International Brigades during the Spanish Civil War.
  • B. Jacques Molénat
    Jacques Molénat is a French journalist best known as one of the founders of the press freedom organization Reporters Without Borders.
  • C. Jacques Bompard
    Jacques Bompard is a French far-right politician known for his long tenure as mayor of Orange and his involvement with nationalist political movements.
  • D. Maurice Bailloud
    Maurice Bailloud was a French sports official best known for delivering the judges' oath at the 1960 Summer Olympics in Rome.
  • E. Georges Récipon
    Georges Récipon was a French sculptor best known for his ornate allegorical sculptures and monumental works in Paris during the late 19th and early 20th centuries.
  • 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_69c687e9ad288190bae5bcac9c8ac855 completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c68ad1c46c819089db43e7c3a8d160 completed March 27, 2026, 1:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69cfdb6942ec8190a8326a98b1cd4e50 completed April 3, 2026, 3:23 p.m.
Created at: March 27, 2026, 1:42 p.m.