Triple

T20658465
Position Surface form Disambiguated ID Type / Status
Subject South Somerset E507690 entity
Predicate containsSettlement P847 FINISHED
Object Langport 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: Langport | Statement: [South Somerset, containsSettlement, Langport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Langport
Context triple: [South Somerset, containsSettlement, Langport]
  • A. Langport chosen
    Langport is a small historic market town in Somerset, England, known for its medieval heritage and strategic location by the River Parrett.
  • B. Lydford
    Lydford is a historic village on the western edge of Dartmoor in Devon, England, known for its medieval castle, dramatic gorge, and scenic river landscapes.
  • C. Frampton-on-Severn
    Frampton-on-Severn is a picturesque village in Gloucestershire, England, known for its large village green and historic Cotswold stone buildings.
  • D. Wiveliscombe
    Wiveliscombe is a small market town in Somerset, England, known for its rural character and historic architecture.
  • E. Droitwich
    Droitwich is a historic spa town in Worcestershire, England, long known for its salt springs and brine baths.
  • 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_69e0b4bf58c081908e52a4500e03ff83 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6b2eefd5c8190a71d4be690a6ae0e completed April 20, 2026, 11:12 p.m.
Created at: April 16, 2026, 11:43 a.m.