Triple

T12975841
Position Surface form Disambiguated ID Type / Status
Subject Vinci SA E321520 entity
Predicate hasSubsidiary P254 FINISHED
Object Arcour E853803 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: Arcour | Statement: [Vinci SA, hasSubsidiary, Arcour]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Arcour
Context triple: [Vinci SA, hasSubsidiary, Arcour]
  • A. Arcour chosen
    Arcour is a French motorway concession company associated with the Vinci Autoroutes network.
  • B. Arcop
    Arcop was a prominent Canadian architectural firm known for its modernist designs and major cultural and institutional projects across Canada.
  • C. Founex
    Founex is a small Swiss municipality on Lake Geneva in the canton of Vaud, known for its residential character and proximity to Geneva.
  • D. Arcore
    Arcore is a small town in the Lombardy region of northern Italy, known for its historic villas and proximity to Milan.
  • E. Ducrot
    Ducrot is a French surname most notably borne by Auguste-Alexandre Ducrot, a 19th-century French general.
  • 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_69d80763bd6c819094437da5b20b01d2 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69d97e48c0208190bb7ec80780480b37 completed April 10, 2026, 10:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6b8ec821c81909398d8e02d69dcbf completed May 3, 2026, 2:54 a.m.
Created at: April 9, 2026, 8:37 p.m.