Triple

T17702547
Position Surface form Disambiguated ID Type / Status
Subject Verchères E441343 entity
Predicate roadAccessVia P9041 FINISHED
Object Autoroute 30 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: Autoroute 30 | Statement: [Verchères, roadAccessVia, Autoroute 30]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Autoroute 30
Context triple: [Verchères, roadAccessVia, Autoroute 30]
  • A. Autoroute 30 chosen
    Autoroute 30 is a major controlled-access highway in the province of Quebec, Canada, forming part of a bypass route around the Montreal metropolitan area.
  • B. Autoroute 50
    Autoroute 50 is a major Quebec highway that runs through the province’s Outaouais and Laurentides regions, linking communities north of the Ottawa River.
  • C. Autoroute 55
    Autoroute 55 is a major north–south highway in Quebec, Canada, connecting several key cities and regions across the province.
  • D. Autoroute 15
    Autoroute 15 is a major north–south highway in Quebec, Canada, connecting the Montreal area to the Laurentians and other northern regions.
  • E. Autoroute 19
    Autoroute 19 is a major Quebec highway that connects Montreal to the Laval region and serves as an important north–south commuter route.
  • 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_69d8b9ea20b48190ace88bb46b01e6a9 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e4715c3980819094b080a871df1100 completed April 19, 2026, 6:08 a.m.
Created at: April 10, 2026, 10:05 a.m.