Triple

T2636581
Position Surface form Disambiguated ID Type / Status
Subject Somerset E59760 entity
Predicate hasTown P847 FINISHED
Object Crewkerne
Crewkerne is a historic market town in South West England known for its traditional architecture and rural surroundings.
 E283620 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: Crewkerne | Statement: [Somerset, hasTown, Crewkerne]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Crewkerne
Context triple: [Somerset, hasTown, Crewkerne]
  • A. Cuckfield
    Cuckfield is a historic village and civil parish in the Mid Sussex district of West Sussex, England, known for its picturesque High Street and traditional English character.
  • B. Okehampton
    Okehampton is a historic market town in Devon, England, known for its medieval castle and role as a former parliamentary borough.
  • C. Knelston
    Knelston is a small rural village located on the Gower Peninsula in South Wales, known for its scenic coastal surroundings and traditional Welsh character.
  • D. Larkhill
    Larkhill is a major British Army garrison on Salisbury Plain in Wiltshire, England, best known as a principal base and training area for the Royal Artillery.
  • E. Yarnton
    Yarnton is a rural village in Oxfordshire, England, known for its historic church, manor house, and proximity to the city of Oxford.
  • 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: Crewkerne
Triple: [Somerset, hasTown, Crewkerne]
Generated description
Crewkerne is a historic market town in South West England known for its traditional architecture and rural surroundings.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Crewkerne
Target entity description: Crewkerne is a historic market town in South West England known for its traditional architecture and rural surroundings.
  • A. Cuckfield
    Cuckfield is a historic village and civil parish in the Mid Sussex district of West Sussex, England, known for its picturesque High Street and traditional English character.
  • B. Okehampton
    Okehampton is a historic market town in Devon, England, known for its medieval castle and role as a former parliamentary borough.
  • C. Knelston
    Knelston is a small rural village located on the Gower Peninsula in South Wales, known for its scenic coastal surroundings and traditional Welsh character.
  • D. Larkhill
    Larkhill is a major British Army garrison on Salisbury Plain in Wiltshire, England, best known as a principal base and training area for the Royal Artillery.
  • E. Yarnton
    Yarnton is a rural village in Oxfordshire, England, known for its historic church, manor house, and proximity to the city of Oxford.
  • 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_69ab4ac8596c8190b34997e73d9e991c completed March 6, 2026, 9:44 p.m.
NER Named-entity recognition batch_69abd8e1fffc81908e4921690098c8db completed March 7, 2026, 7:50 a.m.
NED1 Entity disambiguation (via context triple) batch_69af90b3e9b48190857ae21022a4fb15 completed March 10, 2026, 3:32 a.m.
NEDg Description generation batch_69af922043508190a9a9ceced2425109 completed March 10, 2026, 3:38 a.m.
NED2 Entity disambiguation (via description) batch_69af927bb1d0819081ab11eb4470e28d completed March 10, 2026, 3:39 a.m.
Created at: March 6, 2026, 9:50 p.m.