Triple

T20099086
Position Surface form Disambiguated ID Type / Status
Subject Lyon tramway network E496483 entity
Predicate hasLine P35 FINISHED
Object Rhônexpress 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: Rhônexpress | Statement: [Lyon tramway network, hasLine, Rhônexpress]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rhônexpress
Context triple: [Lyon tramway network, hasLine, Rhônexpress]
  • A. Rhônexpress chosen
    Rhônexpress is an express tram-train service in Lyon, France, that links the city center with Lyon–Saint-Exupéry Airport.
  • B. Liverpool Express
    Liverpool Express is a British pop-rock band from Liverpool known for their melodic 1970s hits such as "You Are My Love" and "Every Man Must Have a Dream."
  • C. Windsor Express
    Windsor Express is a professional basketball team based in Windsor, Ontario, competing in the National Basketball League of Canada.
  • D. Kentish Express
    Kentish Express is a local newspaper serving Ashford and the surrounding area in Kent, England.
  • E. The Railway
    The Railway is an 1873 oil painting by Édouard Manet depicting a woman and a young girl by a Paris train station, notable for its modern urban subject and unconventional composition.
  • 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_69da626eee3881909f3454986d4a6511 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e6666e306c81909c0ef617e0f6fccf completed April 20, 2026, 5:46 p.m.
Created at: April 11, 2026, 11:26 p.m.