Triple

T21346763
Position Surface form Disambiguated ID Type / Status
Subject Villebon-sur-Yvette E526358 entity
Predicate sharesBorderWith P224 FINISHED
Object Orsay 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: Orsay | Statement: [Villebon-sur-Yvette, sharesBorderWith, Orsay]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Orsay
Context triple: [Villebon-sur-Yvette, sharesBorderWith, Orsay]
  • A. Orsay chosen
    Orsay is a commune in the southern suburbs of Paris, France, known for hosting part of the Paris-Saclay University and several major scientific research institutions.
  • B. Orsay
    Orsay is a small uninhabited island off the southwest coast of Islay in Scotland, known for its historic lighthouse and rugged coastal scenery.
  • C. Saclay
    Saclay is a French commune in the Île-de-France region, known for hosting part of the Paris-Saclay research and university cluster.
  • D. Place Jussieu
    Place Jussieu is a public square in central Paris best known for hosting the Jussieu campus of Sorbonne University and several major scientific institutions.
  • E. d'Orsay
    d'Orsay is a French noble family name historically associated with aristocratic figures such as the 19th-century dandy and socialite Louis-Philippe, comte d'Orsay.
  • 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_69e0b51cd5cc81909ac1187971e8a8ad completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69ee5ba8f1c8819089c5d753876b44d5 completed April 26, 2026, 6:38 p.m.
Created at: April 16, 2026, 4:55 p.m.