Triple

T739522
Position Surface form Disambiguated ID Type / Status
Subject General Post Office, Dublin E15211 entity
Predicate operator P179 FINISHED
Object An Post E87842 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: An Post | Statement: [General Post Office, Dublin, operator, An Post]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: An Post
Context triple: [General Post Office, Dublin, operator, An Post]
  • A. An Post chosen
    An Post is Ireland’s state-owned postal service provider, responsible for nationwide mail delivery, post offices, and related financial and communication services.
  • B. Ulster Bank
    Ulster Bank is a major commercial bank in Northern Ireland and the Republic of Ireland, historically part of the Royal Bank of Scotland Group, providing retail and corporate banking services.
  • C. Aer Lingus
    Aer Lingus is the flag carrier airline of Ireland, operating international flights primarily between Ireland, Europe, and North America.
  • D. FirstGroup
    FirstGroup is a major UK-based transport operator that runs bus and rail services across the United Kingdom and North America.
  • E. British Post Office
    The British Post Office was the United Kingdom’s former state-run postal and telecommunications service, responsible for mail delivery, post offices, and early telegraph and telephone systems.
  • 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_69a49358aa308190adbc9b5a0a2adcf9 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a5f3b6388190b5ca3fa31416b61a completed March 1, 2026, 8:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69a654e40b9c8190ab4314e63826d00a completed March 3, 2026, 3:26 a.m.
Created at: March 1, 2026, 7:37 p.m.