Triple

T15334439
Position Surface form Disambiguated ID Type / Status
Subject St. Andrew Parish E366625 entity
Predicate contains P35 FINISHED
Object Irish Town E334138 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: Irish Town | Statement: [St. Andrew Parish, contains, Irish Town]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Irish Town
Context triple: [St. Andrew Parish, contains, Irish Town]
  • A. Irish Town chosen
    Irish Town is a small settlement within the Parish of St. Andrew, known as a local community area in that region.
  • B. Irish Town
    Irish Town is a historic street and commercial area in Gibraltar known for its shops, offices, and colonial-era architecture.
  • C. Irishtown
    Irishtown is a historic district in Limerick, Ireland, known as one of the city’s original medieval quarters.
  • D. Irishtown
    Irishtown is a residential suburb on the south side of Dublin, Ireland, known for its historic village character and proximity to the city’s docklands and coastline.
  • E. Finstown
    Finstown is a small village on Mainland, the largest island of Orkney in Scotland, serving as a local residential and service hub between Kirkwall and Stromness.
  • 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_69d85a121520819093dcce999fdefe1a completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03e03c5f081908e4d14dbdbc7f7a6 completed April 16, 2026, 1:40 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff01ee7480819080133a9910a2bf52 completed May 9, 2026, 9:44 a.m.
Created at: April 10, 2026, 3:17 a.m.