Triple

T11060901
Position Surface form Disambiguated ID Type / Status
Subject Māori electorates E261503 entity
Predicate hasElectorate P11212 FINISHED
Object Te Tai Tonga E589797 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: Te Tai Tonga | Statement: [Māori electorates, hasElectorate, Te Tai Tonga]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Te Tai Tonga
Context triple: [Māori electorates, hasElectorate, Te Tai Tonga]
  • A. Te Tai Tonga chosen
    Te Tai Tonga is a New Zealand Māori parliamentary electorate that covers the entire South Island and parts of the lower North Island.
  • B. Tuʻi Tonga
    Tuʻi Tonga was the sacred royal title of the ancient Tongan kings who held both political authority and divine status at the center of a powerful Polynesian maritime empire.
  • C. Tongaat
    Tongaat is a town in KwaZulu-Natal, South Africa, known for its significant Indian community and sugar industry.
  • D. Pangaimotu
    Pangaimotu is a small island in the Vavaʻu island group of Tonga, known for its tranquil beaches and traditional Tongan village life.
  • E. Gwembe Tonga
    Gwembe Tonga is a regional dialect of the Tonga language spoken primarily by communities in the Gwembe Valley region of southern Zambia.
  • 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_69d6aa98650481908609c7c56bfa7902 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d798e991848190b07c2f48dae38681 completed April 9, 2026, 12:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69e3c887d2148190b19c91b6eb548494 completed April 18, 2026, 6:08 p.m.
Created at: April 8, 2026, 9:26 p.m.