Triple

T13584874
Position Surface form Disambiguated ID Type / Status
Subject Wetherden E324522 entity
Predicate locatedNear P294 FINISHED
Object Haughley E330436 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: Haughley | Statement: [Wetherden, locatedNear, Haughley]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Haughley
Context triple: [Wetherden, locatedNear, Haughley]
  • A. Haughley chosen
    Haughley is a historic village and civil parish in the English county of Suffolk, known for its medieval castle earthworks and traditional rural character.
  • B. Grayshott
    Grayshott is a village in Hampshire, England, known as the birthplace of actor Colin Firth.
  • C. Hawkhurst
    Hawkhurst is a historic village in Kent, England, known for its picturesque Wealden countryside setting and its association with the 18th-century Hawkhurst Gang of smugglers.
  • D. Hadleigh
    Hadleigh is a historic market town in Suffolk, England, known for its medieval buildings and traditional rural character.
  • E. Hadleigh
    Hadleigh is a town in Essex, England, known for its historic castle ruins and position within the borough of Castle Point.
  • 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_69d80769100c819099111274614f5ed2 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbb03310fc819092a56b9f2d73f560 completed April 12, 2026, 2:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69f76bc148d08190821614a866d1a7f0 completed May 3, 2026, 3:37 p.m.
Created at: April 9, 2026, 9:49 p.m.