Triple

T17006922
Position Surface form Disambiguated ID Type / Status
Subject Department of Posts and Telegraphs E412594 entity
Predicate operatedTelecomNetwork P5033 FINISHED
Object national telephone network of Ireland LITERAL 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: national telephone network of Ireland | Statement: [Department of Posts and Telegraphs, operatedTelecomNetwork, national telephone network of Ireland]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: operatedTelecomNetwork
Context triple: [Department of Posts and Telegraphs, operatedTelecomNetwork, national telephone network of Ireland]
  • A. operatedInNetwork
    Indicates that an entity carried out its activities or services within a specified network or system.
  • B. wirelessOperator
    Indicates that an entity operates, manages, or provides services for a wireless communication system or network for another entity.
  • C. operatesNetwork chosen
    Indicates that an entity manages, controls, or runs the functioning of a network.
  • D. telecommunicationsProvider
    Indicates that one entity provides telecommunications services (such as phone, internet, or data connectivity) to another entity.
  • E. USOperator
    Indicates that an entity operates, manages, or provides services within the United States.
  • F. None of above.

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_69d886cb581c8190ab05f4b429c9cd85 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d3841e48819086dbc383cb4b1c16 completed April 18, 2026, 6:55 p.m.
PD Predicate disambiguation batch_69e35d552bc08190af17ef7659e094ef completed April 18, 2026, 10:30 a.m.
Created at: April 10, 2026, 5:32 a.m.