Triple

T14556213
Position Surface form Disambiguated ID Type / Status
Subject Rennes Metro E341548 entity
Predicate operator P179 FINISHED
Object Keolis Rennes E27063 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: Keolis Rennes | Statement: [Rennes Metro, operator, Keolis Rennes]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Keolis Rennes
Context triple: [Rennes Metro, operator, Keolis Rennes]
  • A. Keolis chosen
    Keolis is a major French public transport operator that manages and operates bus, tram, metro, and rail networks in numerous cities worldwide.
  • B. Keolis Downer
    Keolis Downer is a major Australian public transport operator formed as a joint venture between Keolis (France) and Downer Group (Australia), running various rail, tram, and bus services across the country.
  • C. SYTRAL Mobilités
    SYTRAL Mobilités is the public transport authority for the Lyon metropolitan area in France, overseeing and organizing local transit networks including buses, trams, metros, and specialized services.
  • D. Bolloré Group
    Bolloré Group is a French multinational conglomerate best known for its diversified interests in logistics, media, and communications, and for being controlled by the Bolloré family.
  • E. Systra
    Systra is a global engineering and consulting firm specializing in mass transit and rail infrastructure projects.
  • 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_69d822db9c8481908213ceb39585f792 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb2f1490881908673f429e5288c86 completed April 14, 2026, 9:34 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd8abde0308190819da6867e703ea7 completed May 8, 2026, 7:03 a.m.
Created at: April 10, 2026, 1:23 a.m.