Triple

T22917573
Position Surface form Disambiguated ID Type / Status
Subject Georges St-Pierre E568773 entity
Predicate trainedUnder P36609 FINISHED
Object Firas Zahabi 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: Firas Zahabi | Statement: [Georges St-Pierre, trainedUnder, Firas Zahabi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Firas Zahabi
Context triple: [Georges St-Pierre, trainedUnder, Firas Zahabi]
  • A. Firas Zahabi chosen
    Firas Zahabi is a renowned mixed martial arts coach and head trainer at Montreal’s Tristar Gym, best known for guiding the career of UFC legend Georges St-Pierre.
  • B. Omar Meheshi
    Omar Meheshi was a Libyan military officer and political figure who participated in the 1969 coup that brought Muammar Gaddafi to power and later became a prominent dissident against his regime.
  • C. Saad Haddad
    Saad Haddad was a Lebanese militia leader and army officer who founded and commanded the Israeli-backed South Lebanon Army during the Lebanese Civil War.
  • D. Firas Tlass
    Firas Tlass is a Syrian businessman and member of the prominent Tlass family, known for his connections to the country’s political and economic elite.
  • E. Marwan Kenzari
    Marwan Kenzari is a Dutch-Tunisian actor known for his roles in international films such as Disney’s live-action Aladdin and various Hollywood thrillers and dramas.
  • 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_69e2458d90c88190a58cead4e781ca6a completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1807b254c8190bb84596dcacaa35e completed April 29, 2026, 3:52 a.m.
Created at: April 17, 2026, 3:42 p.m.