Triple

T80624
Position Surface form Disambiguated ID Type / Status
Subject Shrewsbury, Shropshire, England E1618 entity
Predicate hasTwinTown P919 FINISHED
Object Tulle
Tulle is a historic town in central France, known as the capital of the Corrèze department in the Nouvelle-Aquitaine region.
 E12829 NE FINISHED

How this triple was built (4 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, Shropshire, England, hasTwinTown, Tulle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Tulle
Context triple: [Shrewsbury, Shropshire, England, hasTwinTown, Tulle]
  • A. Gweru
    Gweru is a central Zimbabwean city that serves as the capital of the Midlands Province and an important commercial and transportation hub.
  • B. Bladon
    Bladon is a village in Oxfordshire, England, best known as the burial place of Sir Winston Churchill.
  • C. Ngäbere
    Ngäbere is an indigenous Chibchan language spoken primarily by the Ngäbe people in Panama and parts of Costa Rica.
  • D. Collex-Bossy
    Collex-Bossy is a small municipality in the canton of Geneva in southwestern Switzerland, known for its rural character and proximity to the French border.
  • E. Ouvrage Schoenenbourg
    Ouvrage Schoenenbourg is a major fortified artillery work of the Maginot Line in northeastern France, notable for its extensive underground galleries, combat blocks, and well-preserved World War II defenses.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Tulle
Triple: [Shrewsbury, Shropshire, England, hasTwinTown, Tulle]
Generated description
Tulle is a historic town in central France, known as the capital of the Corrèze department in the Nouvelle-Aquitaine region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Tulle
Target entity description: Tulle is a historic town in central France, known as the capital of the Corrèze department in the Nouvelle-Aquitaine region.
  • A. Gweru
    Gweru is a central Zimbabwean city that serves as the capital of the Midlands Province and an important commercial and transportation hub.
  • B. Bladon
    Bladon is a village in Oxfordshire, England, best known as the burial place of Sir Winston Churchill.
  • C. Ngäbere
    Ngäbere is an indigenous Chibchan language spoken primarily by the Ngäbe people in Panama and parts of Costa Rica.
  • D. Collex-Bossy
    Collex-Bossy is a small municipality in the canton of Geneva in southwestern Switzerland, known for its rural character and proximity to the French border.
  • E. Ouvrage Schoenenbourg
    Ouvrage Schoenenbourg is a major fortified artillery work of the Maginot Line in northeastern France, notable for its extensive underground galleries, combat blocks, and well-preserved World War II defenses.
  • F. None of above. chosen

Provenance (5 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_69a24c60d19c8190a1b6c105ca59ef5b completed Feb. 28, 2026, 2:01 a.m.
NER Named-entity recognition batch_69a24f354d088190972791051d2d99f8 completed Feb. 28, 2026, 2:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69a29178a7348190a8cb9096ddc7c53e completed Feb. 28, 2026, 6:55 a.m.
NEDg Description generation batch_69a293f9536c8190a261c48d5d8c66a6 completed Feb. 28, 2026, 7:06 a.m.
NED2 Entity disambiguation (via description) batch_69a294ee818081909713af424cbd53d1 completed Feb. 28, 2026, 7:10 a.m.
Created at: Feb. 28, 2026, 2:06 a.m.