Triple

T12218902
Position Surface form Disambiguated ID Type / Status
Subject Selwyn District E291158 entity
Predicate hasSettlement P1068 FINISHED
Object Leeston E963313 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: Leeston | Statement: [Selwyn District, hasSettlement, Leeston]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Leeston
Context triple: [Selwyn District, hasSettlement, Leeston]
  • A. Leeston chosen
    Leeston is a small rural township in the Canterbury region of New Zealand’s South Island, serving as a service and agricultural hub for the surrounding farming communities.
  • B. Carnlough
    Carnlough is a small coastal village in County Antrim, Northern Ireland, known for its picturesque harbour and location along the Antrim Coast Road.
  • C. Rainworth
    Rainworth is a village in Nottinghamshire, England, known as a residential community near the town of Mansfield.
  • D. Garvagh
    Garvagh is a small village in Northern Ireland known for its historic main street and rural setting within County Londonderry.
  • E. Portglenone
    Portglenone is a small village in Northern Ireland known for its riverside setting on the River Bann and its historic monastic and woodland surroundings.
  • 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_69d6ab65923081909acfc61b7a612233 completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d91c951f5881908db6edfda1153d6f completed April 10, 2026, 3:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69f60aa4f4388190a787dde12190c51a completed May 2, 2026, 2:31 p.m.
Created at: April 8, 2026, 9:51 p.m.