Triple

T14262354
Position Surface form Disambiguated ID Type / Status
Subject Westland region E353552 entity
Predicate containsTown P847 FINISHED
Object Haast E901651 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: Haast | Statement: [Westland region, containsTown, Haast]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Haast
Context triple: [Westland region, containsTown, Haast]
  • A. Haast chosen
    Haast is a small, remote township on the wild West Coast of New Zealand’s South Island, known as a gateway to rugged beaches, rainforests, and the Haast World Heritage Area.
  • B. Hasketon
    Hasketon is a small rural village and civil parish in Suffolk, England, known for its historic church and countryside setting near Woodbridge.
  • C. Hakstol
    Hakstol is a surname most notably associated with Dave Hakstol, a Canadian professional ice hockey coach.
  • D. Hareid
    Hareid is a coastal village and municipality in western Norway known for its maritime industries and scenic fjord landscape.
  • E. Haukio
    Haukio is a Finnish surname most notably borne by Jenni Haukio, a poet and the spouse of Finland’s president.
  • 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_69d8278c43e08190824146f4632b89a5 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de63563fc88190b0abdbf8529c65eb completed April 14, 2026, 3:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd326367348190b4b31b32f4ca5639 completed May 8, 2026, 12:46 a.m.
Created at: April 10, 2026, 1:09 a.m.