Triple

T22156882
Position Surface form Disambiguated ID Type / Status
Subject Mapua E547560 entity
Predicate hasViewOf P854 FINISHED
Object Richmond Range 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: Richmond Range | Statement: [Mapua, hasViewOf, Richmond Range]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Richmond Range
Context triple: [Mapua, hasViewOf, Richmond Range]
  • A. Richmond Range chosen
    Richmond Range is a mountain range in the northern South Island of New Zealand, known for its rugged terrain and native forest.
  • B. Richmond Range
    Richmond Range is a forested mountain range in northern New South Wales, Australia, known for its national park, scenic drives, and bushwalking opportunities.
  • C. Burnett Range
    Burnett Range is a mountain range in Queensland, Australia, that forms the headwaters of the Burnett River.
  • D. Egan Range
    The Egan Range is a long, north–south trending mountain range in eastern Nevada known for its rugged terrain and high desert landscapes.
  • E. Cockburn Range
    Cockburn Range is a striking sandstone escarpment in Western Australia’s remote Kimberley region, known for its rugged cliffs and vivid red rock formations.
  • 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_69e11e3b52088190ad5df386d01eb2fb completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f12a29eb848190b0531ce7e45b1003 completed April 28, 2026, 9:44 p.m.
Created at: April 16, 2026, 8:33 p.m.