Triple

T18438964
Position Surface form Disambiguated ID Type / Status
Subject Egmont National Park E450472 entity
Predicate hasWildlife P965 FINISHED
Object tūī 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: tūī | Statement: [Egmont National Park, hasWildlife, tūī]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: tūī
Context triple: [Egmont National Park, hasWildlife, tūī]
  • A. tūī chosen
    The tūī is a distinctive New Zealand songbird known for its iridescent plumage, complex vocalizations, and important role as a native forest pollinator.
  • B. Tangata manu
    Tangata manu was a ritual title and competition on Easter Island in which a champion retrieved the first sooty tern egg of the season to gain prestige and authority for his clan.
  • C. Manuk
    Manuk is a remote volcanic island in Indonesia’s Banda Sea, known for its active volcano and large seabird colonies.
  • D. New Zealand fantail
    The New Zealand fantail is a small, insect-eating songbird native to New Zealand, easily recognized by its fanned tail and agile, fluttering flight through forests and gardens.
  • E. takahe
    The takahē is a large, flightless, and brightly colored rail endemic to New Zealand, once thought extinct and now the focus of intensive conservation efforts.
  • 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_69d8d381d6388190a9e94e9c658174e4 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e51c0ed6708190ae90efd8455ec352 completed April 19, 2026, 6:16 p.m.
Created at: April 10, 2026, 11:30 a.m.