Triple

T20710327
Position Surface form Disambiguated ID Type / Status
Subject .nz E509019 entity
Predicate sponsoringOrganization P3853 FINISHED
Object InternetNZ 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: InternetNZ | Statement: [.nz, sponsoringOrganization, InternetNZ]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: InternetNZ
Context triple: [.nz, sponsoringOrganization, InternetNZ]
  • A. InternetNZ chosen
    InternetNZ is the non-profit organization responsible for managing New Zealand’s .nz country-code top-level domain and promoting an open and secure internet in New Zealand.
  • B. Internet in New Zealand
    Internet in New Zealand refers to the nationwide digital network infrastructure, services, and usage patterns that connect New Zealanders to online resources and global communications.
  • C. .nz
    .nz is the country code top-level domain (ccTLD) used for websites associated with New Zealand.
  • D. Stuff.co.nz
    Stuff.co.nz is a major New Zealand news and media website providing national and international news, opinion, and multimedia content.
  • E. NZNS
    NZNS is the ICAO airport code for Nelson Airport, a regional airport serving the city of Nelson in New Zealand.
  • 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_69e0b4c40ad88190b81f77695366d328 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c1974ba08190b0e5ad529be95e4c completed April 21, 2026, 12:15 a.m.
Created at: April 16, 2026, 12:14 p.m.