Triple

T17572491
Position Surface form Disambiguated ID Type / Status
Subject Ngāti Hei E427973 entity
Predicate hasAncestralConnectionTo P7844 FINISHED
Object Whitianga 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: Whitianga | Statement: [Ngāti Hei, hasAncestralConnectionTo, Whitianga]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Whitianga
Context triple: [Ngāti Hei, hasAncestralConnectionTo, Whitianga]
  • A. Whitianga chosen
    Whitianga is a coastal town and popular holiday destination on New Zealand’s North Island, known for its beaches, fishing, and access to nearby natural attractions.
  • B. Winya
    Winya is a small rural town located within Queensland’s Somerset Region in Australia.
  • C. Waihind
    Waihind was an important early medieval city in the Kabul–Gandhara region that served as a major political and cultural center of the Hindu Shahi rulers in northwestern South Asia.
  • D. Tinana
    Tinana is a small town and suburb in Queensland, Australia, located near Maryborough in the Fraser Coast Region.
  • E. Waigali
    Waigali is a Nuristani language spoken by the Waigal Valley communities in eastern Afghanistan, known for preserving archaic features distinct from surrounding Indo-Aryan and Iranian languages.
  • 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_69d889e0385081908a04b66f4dd4bd0d completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e459324aa48190ae23fcae6e8919f8 completed April 19, 2026, 4:25 a.m.
Created at: April 10, 2026, 5:50 a.m.