Triple

T1474340
Position Surface form Disambiguated ID Type / Status
Subject Shrewsbury E30803 entity
Predicate hasTwinTown P919 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: [Shrewsbury, hasTwinTown, Tulle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tulle
Context triple: [Shrewsbury, hasTwinTown, 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_69a498fe55a88190ab7f9e40ace88e49 completed March 1, 2026, 7:52 p.m.
NER Named-entity recognition batch_69a4c6011d248190988380eca4ecf514 completed March 1, 2026, 11:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69ad15a98b4c819082bd7aa8e0c82de9 completed March 8, 2026, 6:22 a.m.
Created at: March 1, 2026, 8:11 p.m.