Triple

T20626347
Position Surface form Disambiguated ID Type / Status
Subject Great Northern Railway (Ireland) E506827 entity
Predicate servedCity P3936 FINISHED
Object Portadown 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: Portadown | Statement: [Great Northern Railway (Ireland), servedCity, Portadown]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Portadown
Context triple: [Great Northern Railway (Ireland), servedCity, Portadown]
  • A. Portadown chosen
    Portadown is a town in County Armagh, Northern Ireland, historically known as an industrial and railway hub and now part of the Craigavon urban area.
  • B. Ballymena
    Ballymena is a town in County Antrim, Northern Ireland, known as the birthplace of actor Liam Neeson and for its historic market and surrounding rural landscapes.
  • C. Hoskinstown
    Hoskinstown is a small rural locality in New South Wales, Australia, situated in the Southern Tablelands near the city of Queanbeyan.
  • D. Ballyclare
    Ballyclare is a small town in County Antrim, Northern Ireland, known for its local football culture and community-centered character.
  • E. Lurgan
    Lurgan is a town in County Armagh, Northern Ireland, known historically for its linen industry and its proximity to Lough Neagh.
  • 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_69e0b4bd4a0081908d4e97a590a33fb2 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6abe576c081909231dc0d7304b9a9 completed April 20, 2026, 10:42 p.m.
Created at: April 16, 2026, 11:42 a.m.