Triple

T21291890
Position Surface form Disambiguated ID Type / Status
Subject La Doua E524812 entity
Predicate hostsInstitution P186 FINISHED
Object CPE Lyon 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: CPE Lyon | Statement: [La Doua, hostsInstitution, CPE Lyon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: CPE Lyon
Context triple: [La Doua, hostsInstitution, CPE Lyon]
  • A. CPE Lyon chosen
    CPE Lyon is a French grande école of engineering and chemistry located in the Lyon metropolitan area.
  • B. TER Lyon–Grenoble
    TER Lyon–Grenoble is a regional train service in France that connects the cities of Lyon and Grenoble as part of the TER Auvergne-Rhône-Alpes network.
  • C. Parc Olympique Lyonnais
    Parc Olympique Lyonnais is a modern football stadium in Décines-Charpieu near Lyon, France, serving as a major venue for domestic and international sporting and entertainment events.
  • D. MHC Lyons
    MHC Lyons is an Irish architectural firm known for its contemporary designs and contributions to modern urban development.
  • E. FC Lyon
    FC Lyon is a historic French football club based in Lyon, known as one of the country’s older sporting institutions.
  • 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_69e0b5171f6c8190a5d57201ede73811 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e736da28648190ae3f63c6ba1f6d6f completed April 21, 2026, 8:35 a.m.
Created at: April 16, 2026, 4:04 p.m.