Triple

T19797514
Position Surface form Disambiguated ID Type / Status
Subject Dickon E475581 entity
Predicate familyName P18 FINISHED
Object Sowerby 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: Sowerby | Statement: [Dickon, familyName, Sowerby]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sowerby
Context triple: [Dickon, familyName, Sowerby]
  • A. Sowerby chosen
    Sowerby is a village in Calderdale, West Yorkshire, England, known for its hillside setting above the Calder Valley and its historic stone-built architecture.
  • B. Sandwick
    Sandwick is a small settlement associated with the area of Martindale, likely a rural hamlet or village in the United Kingdom.
  • C. Sandwick
    Sandwick is a rural parish in Orkney, Scotland, known for its coastal landscapes and proximity to several important Neolithic archaeological sites.
  • D. Sorbie
    Sorbie is a small rural village located in the Machars peninsula of Dumfries and Galloway in southwest Scotland.
  • E. Havenpool
    Havenpool is a fictional town in Thomas Hardy’s Wessex, based on the real port of Poole on England’s south coast.
  • 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_69d8e51b014081908b263e167370529a completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e653c877288190b56ee7eedea710a3 completed April 20, 2026, 4:26 p.m.
Created at: April 10, 2026, 1:49 p.m.