Triple

T17565900
Position Surface form Disambiguated ID Type / Status
Subject Ballinderry River E427811 entity
Predicate crossesSettlement P27425 FINISHED
Object Cookstown 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: Cookstown | Statement: [Ballinderry River, crossesSettlement, Cookstown]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cookstown
Context triple: [Ballinderry River, crossesSettlement, Cookstown]
  • A. Cookstown chosen
    Cookstown is a market town in County Tyrone, Northern Ireland, known historically for its long main street and role as a local commercial center.
  • B. Collinstown
    Collinstown is a suburban area in north County Dublin, Ireland, best known today as the locality encompassing Dublin Airport.
  • C. Edgeworthstown
    Edgeworthstown is a small town in County Longford, Ireland, historically associated with the Anglo-Irish Edgeworth family and writer Maria Edgeworth.
  • D. Carrickmacross
    Carrickmacross is a market town in County Monaghan, Ireland, known for its traditional lace-making and historic architecture.
  • E. Navan
    Navan is a town in County Meath, Ireland, known historically as a market and mining center and now a growing commuter hub for Dublin.
  • 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_69e4592ce42c8190a54a0a328c5e8ffc completed April 19, 2026, 4:25 a.m.
Created at: April 10, 2026, 5:50 a.m.