Triple

T401306
Position Surface form Disambiguated ID Type / Status
Subject Vernier E9287 entity
Predicate hasNeighboringMunicipality P224 FINISHED
Object Onex E29604 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: Onex | Statement: [Vernier, hasNeighboringMunicipality, Onex]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Onex
Context triple: [Vernier, hasNeighboringMunicipality, Onex]
  • A. Onex chosen
    Onex is a suburban municipality in western Switzerland located just outside the city of Geneva.
  • B. Northesk
    Northesk is the territorial designation associated with the Scottish peerage title Earl of Northesk, historically linked to the Carnegie family.
  • C. ONR Global
    ONR Global is the international arm of the U.S. Office of Naval Research that fosters and funds scientific collaboration and innovation with partners around the world to support naval and marine technologies.
  • D. Zanmi Lasante
    Zanmi Lasante is a community-based healthcare organization in rural Haiti that became the flagship site for Paul Farmer’s pioneering model of rights-based, comprehensive medical care for the poor.
  • E. Nexus
    Nexus is the original World Wide Web browser and editor created by Tim Berners-Lee, later renamed from its initial title "WorldWideWeb."
  • 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_69a2e8004cb88190b92ed1add6abf41a completed Feb. 28, 2026, 1:05 p.m.
NER Named-entity recognition batch_69a2ee2c2d1881909aa1ccfaa4172b38 completed Feb. 28, 2026, 1:31 p.m.
NED1 Entity disambiguation (via context triple) batch_69a410410c108190990d4d5ef2e7ff61 completed March 1, 2026, 10:09 a.m.
Created at: Feb. 28, 2026, 1:08 p.m.