Triple

T17572933
Position Surface form Disambiguated ID Type / Status
Subject Isle of Portland E427983 entity
Predicate hasSettlement P1068 FINISHED
Object Southwell 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: Southwell | Statement: [Isle of Portland, hasSettlement, Southwell]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Southwell
Context triple: [Isle of Portland, hasSettlement, Southwell]
  • A. Southwell chosen
    Southwell is a small coastal settlement on the Isle of Portland in Dorset, England, known for its proximity to dramatic cliffs and quarrying heritage.
  • B. Southwell
    Southwell is a historic town in Nottinghamshire, England, best known for its medieval Southwell Minster and picturesque market-town character.
  • C. Steeton
    Steeton is a village in West Yorkshire, England, situated near Keighley in the Aire Valley.
  • D. Ketton
    Ketton is a village and civil parish in Rutland, England, known for its historic limestone quarries and rural character.
  • E. Wolsingham
    Wolsingham is a small historic market town and civil parish in County Durham, England, situated in the rural valley of Weardale.
  • 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_69d889e0385081908a04b66f4dd4bd0d completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e459330c788190907a02fc98e0e24b completed April 19, 2026, 4:25 a.m.
Created at: April 10, 2026, 5:50 a.m.