Triple

T18056852
Position Surface form Disambiguated ID Type / Status
Subject Foyle E432060 entity
Predicate contains P35 FINISHED
Object Creggan 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: Creggan | Statement: [Foyle, contains, Creggan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Creggan
Context triple: [Foyle, contains, Creggan]
  • A. Creggan chosen
    Creggan is a large residential area in Derry, Northern Ireland, historically known as a predominantly nationalist community and a focal point during the Troubles.
  • B. Grenagh
    Grenagh is a small rural village located in the northern part of County Cork, Ireland.
  • C. Charlemont
    Charlemont is a stop on Dublin’s Luas light rail system, serving the Green Line near the city center.
  • D. Baronscourt
    Baronscourt is a historic country estate in County Tyrone, Northern Ireland, serving as the ancestral home of the Dukes of Abercorn.
  • E. Ferbane
    Ferbane is a small town in County Offaly, Ireland, situated near the River Brosna and known historically for its peat-fueled power station and surrounding boglands.
  • 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_69d8b906482481908183315b9ecf9994 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4c103cedc819086a905269b118795 completed April 19, 2026, 11:48 a.m.
Created at: April 10, 2026, 10:26 a.m.