Triple

T17289479
Position Surface form Disambiguated ID Type / Status
Subject USA Perpignan E419745 entity
Predicate hasRivalryWith P893 FINISHED
Object Montpellier Hérault Rugby 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: Montpellier Hérault Rugby | Statement: [USA Perpignan, hasRivalryWith, Montpellier Hérault Rugby]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Montpellier Hérault Rugby
Context triple: [USA Perpignan, hasRivalryWith, Montpellier Hérault Rugby]
  • A. Montpellier Hérault Rugby chosen
    Montpellier Hérault Rugby is a professional French rugby union club based in Montpellier that competes in the country’s top division, the Top 14.
  • B. CS Meyzieu Rugby
    CS Meyzieu Rugby is a French rugby union club based in Meyzieu that competes in the national amateur leagues.
  • C. Stade Toulousain
    Stade Toulousain is a French professional rugby union club based in Toulouse, renowned as one of Europe’s most successful and decorated rugby teams.
  • D. Racing 92 rugby union
    Racing 92 rugby union is a professional French rugby union club based in the Paris region that competes in the Top 14 and European competitions.
  • E. USAP Perpignan
    USAP Perpignan is a professional rugby union club based in Perpignan, France, known for its strong tradition in French and European competitions.
  • 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_69d886db32608190a61e18862c5a8af6 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e43782b7ac8190b702567e9ccf9a35 completed April 19, 2026, 2:01 a.m.
Created at: April 10, 2026, 5:40 a.m.