Triple

T23025351
Position Surface form Disambiguated ID Type / Status
Subject Axminster E573293 entity
Predicate hasPostTown P2711 FINISHED
Object AXMINSTER
AXMINSTER is a market town in Devon, England, historically renowned for its production of high-quality Axminster carpets.
E1566141 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: AXMINSTER | Statement: [Axminster, hasPostTown, AXMINSTER]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: AXMINSTER
Context triple: [Axminster, hasPostTown, AXMINSTER]
  • A. Beaminster
    Beaminster is a small historic market town in Dorset, England, known for its picturesque countryside setting and traditional architecture.
  • B. Minster
    Minster is a coastal town and civil parish on the Isle of Sheppey in Kent, England, known for its historic abbey and seaside character.
  • C. Minster
    Minster is a small village in western Ohio known for its strong German heritage and annual Oktoberfest celebration.
  • D. Minster
    Minster is a village and civil parish in the Thanet district of Kent, England, known for its historic abbey and traditional rural character.
  • E. Whitminster
    Whitminster is a village and civil parish in Gloucestershire, England, situated near the River Severn and close to the town of Stonehouse.
  • 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: AXMINSTER
Triple: [Axminster, hasPostTown, AXMINSTER]
Generated description
AXMINSTER is a market town in Devon, England, historically renowned for its production of high-quality Axminster carpets.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: AXMINSTER
Target entity description: AXMINSTER is a market town in Devon, England, historically renowned for its production of high-quality Axminster carpets.
  • A. Beaminster
    Beaminster is a small historic market town in Dorset, England, known for its picturesque countryside setting and traditional architecture.
  • B. Minster
    Minster is a coastal town and civil parish on the Isle of Sheppey in Kent, England, known for its historic abbey and seaside character.
  • C. Minster
    Minster is a village and civil parish in the Thanet district of Kent, England, known for its historic abbey and traditional rural character.
  • D. Minster
    Minster is a small village in western Ohio known for its strong German heritage and annual Oktoberfest celebration.
  • E. Whitminster
    Whitminster is a village and civil parish in Gloucestershire, England, situated near the River Severn and close to the town of Stonehouse.
  • 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_69e245b821008190b0e09cb02092aae1 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1847c671c8190a8095051d8c3cf93 completed April 29, 2026, 4:09 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0bf2b1cfc081909681be870918ef5b completed May 19, 2026, 5:18 a.m.
NEDg Description generation batch_6a0bf376736481908d6cbe5feb46044b completed May 19, 2026, 5:21 a.m.
NED2 Entity disambiguation (via description) batch_6a0bf404aeb48190962e0e0fcd82c9eb completed May 19, 2026, 5:24 a.m.
Created at: April 17, 2026, 3:52 p.m.