Triple

T17572931
Position Surface form Disambiguated ID Type / Status
Subject Isle of Portland E427983 entity
Predicate hasSettlement P1068 FINISHED
Object Easton 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: Easton | Statement: [Isle of Portland, hasSettlement, Easton]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Easton
Context triple: [Isle of Portland, hasSettlement, Easton]
  • A. Easton
    Easton is a Scottish surname most prominently associated with Grammy-winning pop singer Sheena Easton.
  • B. Easton chosen
    Easton is a village on the Isle of Portland in Dorset, England, known for its historic stone buildings and coastal setting.
  • C. Easton
    Easton is a suburban town in southeastern Massachusetts known for its historic architecture, residential character, and proximity to the Greater Boston area.
  • D. Easton
    Easton is a small, affluent residential town in Fairfield County, southwestern Connecticut, known for its rural character, reservoirs, and extensive open space.
  • E. Easton
    Easton is an inner-city district of Bristol, England, known for its diverse community, vibrant street art, and strong cultural and social activism.
  • 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.