Triple

T17006911
Position Surface form Disambiguated ID Type / Status
Subject Department of Posts and Telegraphs E412594 entity
Predicate dissolvedInto P77 FINISHED
Object An Post 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: An Post | Statement: [Department of Posts and Telegraphs, dissolvedInto, An Post]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: An Post
Context triple: [Department of Posts and Telegraphs, dissolvedInto, 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. Iarnród Éireann
    Iarnród Éireann is the national railway operator of Ireland, responsible for most passenger and freight rail services across the country.
  • C. Bord Gáis Energy
    Bord Gáis Energy is an Irish energy supplier providing gas, electricity, and related services to residential and business customers.
  • D. Bus Éireann
    Bus Éireann is Ireland’s national bus company, providing intercity, regional, and local bus services across the country.
  • E. Telecom Éireann
    Telecom Éireann was Ireland’s former state-owned telecommunications company responsible for providing national telephone and related communication services before its privatization and rebranding as Eircom.
  • 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_69d886cb581c8190ab05f4b429c9cd85 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d3841e48819086dbc383cb4b1c16 completed April 18, 2026, 6:55 p.m.
Created at: April 10, 2026, 5:32 a.m.