Triple

T680019
Position Surface form Disambiguated ID Type / Status
Subject Prévessin-Moëns E13160 entity
Predicate sharesBorderWith P224 FINISHED
Object Vernier E9287 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: Vernier | Statement: [Prévessin-Moëns, sharesBorderWith, Vernier]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Vernier
Context triple: [Prévessin-Moëns, sharesBorderWith, Vernier]
  • A. Vernier chosen
    Vernier is a municipality in the canton of Geneva in southwestern Switzerland, forming part of the Geneva metropolitan area.
  • B. Elster
    Elster is a river in central Europe, primarily flowing through the German state of Saxony and its surrounding regions.
  • C. D.V.I.
    D.V.I. is the standard abbreviation for the District Court of the Virgin Islands, a federal court with jurisdiction over the U.S. Virgin Islands.
  • D. Meraki
    Meraki is a cloud-managed IT company known for its wireless, switching, security, and device management solutions, acquired by and operating as a subsidiary of Cisco.
  • E. Philips Huygens
    Philips Huygens was a member of the prominent Dutch Huygens family of the 17th century, known primarily as a son of the diplomat and poet Constantijn Huygens and brother of the scientist Christiaan Huygens.
  • 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_69a4933d3bf88190972041cd8cf143b9 completed March 1, 2026, 7:27 p.m.
NER Named-entity recognition batch_69a4a04f4efc819082767a7517fa760a completed March 1, 2026, 8:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69a5c3a38b188190802394a35c83b10b completed March 2, 2026, 5:06 p.m.
Created at: March 1, 2026, 7:36 p.m.