Triple

T19986883
Position Surface form Disambiguated ID Type / Status
Subject Autoroute 25 E493955 entity
Predicate connects P390 FINISHED
Object Autoroute 640 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 640 | Statement: [Autoroute 25, connects, Autoroute 640]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Autoroute 640
Context triple: [Autoroute 25, connects, Autoroute 640]
  • A. Autoroute 640 chosen
    Autoroute 640 is a major Quebec highway forming a northern bypass of Montreal, connecting several suburbs along the North Shore.
  • B. Autoroute A64
    Autoroute A64 is a major French motorway in southwestern France that connects Toulouse to Bayonne, serving as an important route between the interior and the Atlantic coast.
  • C. Autoroute A63
    Autoroute A63 is a major motorway in southwestern France that connects Bordeaux to the Spanish border, forming a key segment of the Atlantic coastal route between France and Spain.
  • D. Autoroute A660
    Autoroute A660 is a short French motorway in southwestern France that links the A63 to the Atlantic coast near Arcachon.
  • E. Autoroute A62
    Autoroute A62 is a major French motorway in southwestern France that connects Bordeaux to Toulouse as part of the national autoroute network.
  • 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_69da626a67648190af9653832a3aeced completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e65d16f60c81909ba02c0a3429ecae completed April 20, 2026, 5:06 p.m.
Created at: April 11, 2026, 3:29 p.m.