Triple

T10917029
Position Surface form Disambiguated ID Type / Status
Subject Michelle Yeoh E257849 entity
Predicate spouse P13 FINISHED
Object Jean Todt E623654 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: Jean Todt | Statement: [Michelle Yeoh, spouse, Jean Todt]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jean Todt
Context triple: [Michelle Yeoh, spouse, Jean Todt]
  • A. Jean Todt chosen
    Jean Todt is a French motorsport executive and former rally co-driver best known for leading Ferrari’s Formula 1 team during its dominant Schumacher era and later serving as president of the FIA.
  • B. Giuseppe Cordero Lanza di Montezemolo
    Giuseppe Cordero Lanza di Montezemolo was an Italian army officer and prominent leader in the Roman Resistance during World War II, executed by the Nazis in 1944.
  • C. Claude Agostini
    Claude Agostini is a cinematographer best known for his work on the prehistoric adventure film "Quest for Fire."
  • D. Franck Massard
    Franck Massard is a French local politician who serves as the mayor of the commune of Ambilly in the Haute-Savoie department of eastern France.
  • E. Henri Prost
    Henri Prost was a prominent French architect and urban planner best known for designing major city plans in France, Morocco, and Turkey in the early 20th century.
  • 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_69d6aa864ed88190818280ab6791d065 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d7707deb608190903b1066e19600d3 completed April 9, 2026, 9:25 a.m.
NED1 Entity disambiguation (via context triple) batch_69e216fca9f48190b02e8c13b8f428bf completed April 17, 2026, 11:18 a.m.
Created at: April 8, 2026, 9:22 p.m.