Triple

T3897111
Position Surface form Disambiguated ID Type / Status
Subject Folkestone E90396 entity
Predicate hasNeighbourhood P4813 FINISHED
Object Capel-le-Ferne E326409 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: Capel-le-Ferne | Statement: [Folkestone, hasNeighbourhood, Capel-le-Ferne]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Capel-le-Ferne
Context triple: [Folkestone, hasNeighbourhood, Capel-le-Ferne]
  • A. Capel-le-Ferne chosen
    Capel-le-Ferne is a coastal village in Kent, England, known for its clifftop location above the White Cliffs and its Battle of Britain memorial.
  • B. Capel
    Capel is a rural village and civil parish in Kent, England, situated within the Borough of Tunbridge Wells.
  • C. Capel
    Capel is a rural village and civil parish in the Mole Valley district of Surrey, England.
  • D. Capel St Mary
    Capel St Mary is a village and civil parish in Suffolk, England, situated between Ipswich and Colchester.
  • E. Farleigh
    Farleigh is a village and civil parish in Surrey, England, known for its rural character and historic church.
  • 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_69aed95d315881908cbf1bf4a7215fbf completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aeecd34e608190bf1ca1d0c04562b2 completed March 9, 2026, 3:52 p.m.
NED1 Entity disambiguation (via context triple) batch_69b51c9e3db881909e865e52a842b1be completed March 14, 2026, 8:30 a.m.
Created at: March 9, 2026, 3:21 p.m.