Triple

T3261858
Position Surface form Disambiguated ID Type / Status
Subject Plymouth Sound E68429 entity
Predicate adjacentTo P224 FINISHED
Object Cornwall E112827 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: Cornwall | Statement: [Plymouth Sound, adjacentTo, Cornwall]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cornwall
Context triple: [Plymouth Sound, adjacentTo, Cornwall]
  • A. Cornwall chosen
    Cornwall is a county in the far southwest of England, known for its rugged coastline, Celtic heritage, and popular seaside tourism.
  • B. Cornwall
    Cornwall is a small town in central Prince Edward Island, Canada, located just west of the provincial capital, Charlottetown.
  • C. Devon
    Devon is a county in South West England known for its rugged coastlines, moorland national parks, and historic seaside towns.
  • D. Devon
    Devon is a residential neighbourhood located within the city of Fredericton in New Brunswick, Canada.
  • E. Torbay
    Torbay is a coastal unitary authority and popular seaside resort area in Devon, England, encompassing the towns of Torquay, Paignton, and Brixham.
  • 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_69ad8590444081909e8107a8aeef3a23 completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adafa7fea08190b089b6174fd7cd32 completed March 8, 2026, 5:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5f580e2488190bce70398502e11d4 completed March 14, 2026, 11:55 p.m.
Created at: March 8, 2026, 3:09 p.m.