Triple

T18191774
Position Surface form Disambiguated ID Type / Status
Subject Orange Line (Montreal Metro) E435552 entity
Predicate hasStation P35 FINISHED
Object Sauvé station 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: Sauvé station | Statement: [Orange Line (Montreal Metro), hasStation, Sauvé station]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sauvé station
Context triple: [Orange Line (Montreal Metro), hasStation, Sauvé station]
  • A. Sauvé station chosen
    Sauvé station is a Montreal Metro station on the Orange Line located in the Ahuntsic-Cartierville borough of Montreal, Quebec, Canada.
  • B. Sainte-Anne station
    Sainte-Anne station is an underground metro stop in central Rennes, France, serving as a key node on the Rennes Metro network.
  • C. Beaudry station
    Beaudry station is a Montreal Metro station on the Green Line, known for serving the city’s Gay Village along Sainte-Catherine Street.
  • D. Plamondon station
    Plamondon station is a Montreal Metro station on the Orange Line serving the Côte-des-Neiges–Notre-Dame-de-Grâce borough.
  • E. Les Grésillons station
    Les Grésillons station is a commuter rail stop in the Paris metropolitan area serving the suburb of Argenteuil in northern France.
  • 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_69d8b90c7ec081909b4694ccecb449c6 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4e0d05974819094b4a50d081be881 completed April 19, 2026, 2:04 p.m.
Created at: April 10, 2026, 10:31 a.m.