Triple

T13929857
Position Surface form Disambiguated ID Type / Status
Subject Devizes E334960 entity
Predicate postalTown P2711 FINISHED
Object DEVIZES
DEVIZES is a historic market town in Wiltshire, England, known for its medieval streets, traditional markets, and proximity to the Kennet and Avon Canal.
 E1069854 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: DEVIZES | Statement: [Devizes, postalTown, DEVIZES]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: DEVIZES
Context triple: [Devizes, postalTown, DEVIZES]
  • A. Dees
    Dees is a common nickname for the Melbourne Football Club, an Australian rules football team in the Australian Football League (AFL).
  • B. Deatsville
    Deatsville is a small town in central Alabama known for its rural character and proximity to the Montgomery metropolitan area.
  • C. Davisville
    Davisville was the original name of the city now known as Davis, California, a college town best known as the home of the University of California, Davis.
  • D. Southdene
    Southdene is a residential area and suburb located near the town of Kirkby in Merseyside, England.
  • E. Doveridge
    Doveridge is a village in Derbyshire, England, known for its rural setting near the River Dove and its historic church and traditional English countryside character.
  • 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: DEVIZES
Triple: [Devizes, postalTown, DEVIZES]
Generated description
DEVIZES is a historic market town in Wiltshire, England, known for its medieval streets, traditional markets, and proximity to the Kennet and Avon Canal.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: DEVIZES
Target entity description: DEVIZES is a historic market town in Wiltshire, England, known for its medieval streets, traditional markets, and proximity to the Kennet and Avon Canal.
  • A. Dees
    Dees is a common nickname for the Melbourne Football Club, an Australian rules football team in the Australian Football League (AFL).
  • B. Deatsville
    Deatsville is a small town in central Alabama known for its rural character and proximity to the Montgomery metropolitan area.
  • C. Davisville
    Davisville was the original name of the city now known as Davis, California, a college town best known as the home of the University of California, Davis.
  • D. Southdene
    Southdene is a residential area and suburb located near the town of Kirkby in Merseyside, England.
  • E. Doveridge
    Doveridge is a village in Derbyshire, England, known for its rural setting near the River Dove and its historic church and traditional English countryside character.
  • 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_69d81c5f739081908bc05b2461f54828 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2aa900a0819095eeb1bc46b0336e completed April 14, 2026, 11:53 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7ce8262288190a7e6dd647b1917c1 completed May 3, 2026, 10:38 p.m.
NEDg Description generation batch_69f9fd5b82f48190b0b89ddca25883cc completed May 5, 2026, 2:23 p.m.
NED2 Entity disambiguation (via description) batch_69f9fea0a9dc8190b5b65dfec9626949 completed May 5, 2026, 2:28 p.m.
Created at: April 9, 2026, 10:16 p.m.