Triple

T9911508
Position Surface form Disambiguated ID Type / Status
Subject Kevin De Bruyne E185155 entity
Predicate spouse P13 FINISHED
Object Michele Lacroix E185155 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: Michele Lacroix | Statement: [Kevin De Bruyne, spouse, Michele Lacroix]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Michele Lacroix
Context triple: [Kevin De Bruyne, spouse, Michele Lacroix]
  • A. Michele Lacroix chosen
    Michele Lacroix is a Belgian public figure best known as the wife of professional footballer Kevin De Bruyne.
  • B. Sebastian Thomas Hilfiger
    Sebastian Thomas Hilfiger is a son of American fashion designer and Tommy Hilfiger brand founder Tommy Hilfiger.
  • C. Pierre Caron
    Pierre Caron is a French-Canadian historian and archivist known for his work on the political and social history of New France and Quebec.
  • D. Richard Hilfiger
    Richard Hilfiger is an American actor and musician best known as the son of fashion designer Tommy Hilfiger.
  • E. Olivier Pantaloni
    Olivier Pantaloni is a French former professional footballer and manager best known for his long association with AC Ajaccio, where he has served multiple spells as head coach.
  • 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_69ca8296165881908ca4750701af1f29 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cdb5391b8081908094b88cdde4b55a completed April 2, 2026, 12:15 a.m.
NED1 Entity disambiguation (via context triple) batch_69d228a405908190ad63ebd659779ed7 completed April 5, 2026, 9:17 a.m.
Created at: March 30, 2026, 8:41 p.m.