Triple

T20114830
Position Surface form Disambiguated ID Type / Status
Subject Sompting E490429 entity
Predicate partOf P40 FINISHED
Object Sompting parish NE NERFINISHED

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: Sompting parish | Statement: [Sompting, partOf, Sompting parish]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sompting parish
Context triple: [Sompting, partOf, Sompting parish]
  • A. Sompting chosen
    Sompting is a village and civil parish in West Sussex, England, situated near the south coast between Worthing and Lancing.
  • B. Cullompton
    Cullompton is a historic market town in Devon, England, known for its agricultural heritage and location in the Culm Valley.
  • C. Colerne parish
    Colerne parish is a rural civil parish in Wiltshire, England, characterized by its historic village setting and surrounding countryside.
  • D. Binsted parish
    Binsted parish is a rural civil and ecclesiastical parish in West Sussex, England, centered on the historic Holy Cross Church and its surrounding village community.
  • E. Cottenham
    Cottenham is a large, historic village and civil parish in Cambridgeshire, England, known for its fen-edge location and traditional rural character.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69da62636cc08190982cc71733a17b8d completed April 11, 2026, 3:01 p.m.
NER Named-entity recognition batch_69e666e3f2288190840d1eb431ac9a1b completed April 20, 2026, 5:48 p.m.
Created at: April 11, 2026, 11:29 p.m.