Triple

T2262078
Position Surface form Disambiguated ID Type / Status
Subject Brive-la-Gaillarde E50060 entity
Predicate nearbyCity P350 FINISHED
Object Tulle E12829 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: Tulle | Statement: [Brive-la-Gaillarde, nearbyCity, Tulle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tulle
Context triple: [Brive-la-Gaillarde, nearbyCity, Tulle]
  • A. Tulle chosen
    Tulle is a historic town in central France, known as the capital of the Corrèze department in the Nouvelle-Aquitaine region.
  • B. Tullistes
    Tullistes are the inhabitants of the French city of Tulle, located in the Corrèze department in central France.
  • C. Hollein
    Hollein is a German-language surname most prominently associated with Austrian architects Hans Hollein and his son Max Hollein, a leading museum director.
  • D. Cailliau
    Cailliau is the surname of Robert Cailliau, a Belgian computer scientist known for co-developing the World Wide Web.
  • E. Meliae
    The Meliae are nymphs from Greek mythology associated with ash trees and often linked to the early generations of humanity and rustic woodland life.
  • 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_69a88b01e0048190ba96431b5f990ba9 completed March 4, 2026, 7:41 p.m.
NER Named-entity recognition batch_69abc18be8308190abc4a59d37dfd93a completed March 7, 2026, 6:11 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae71cdacb48190bc11e9e0e6b61ba0 completed March 9, 2026, 7:07 a.m.
Created at: March 4, 2026, 7:48 p.m.