Triple

T4622203
Position Surface form Disambiguated ID Type / Status
Subject Mount Eden E101011 entity
Predicate locatedOn P40 FINISHED
Object North Island E14332 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: North Island | Statement: [Mount Eden, locatedOn, North Island]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: North Island
Context triple: [Mount Eden, locatedOn, North Island]
  • A. North Island chosen
    North Island is one of New Zealand’s two main islands, known for its major cities, volcanic landscapes, and significant cultural and economic centers.
  • B. North Island
    North Island is a volcanic island located within Kenya’s Lake Turkana, known for its stark lava landscapes and unique desert-lake ecosystem.
  • C. King Island
    King Island is a remote island in Bass Strait known for its rugged coastline, rich wildlife, and premium dairy and beef production.
  • D. Northerly Island
    Northerly Island is a man-made peninsula and park on Chicago’s lakefront known for its natural areas, walking trails, and concert venue with views of the city skyline.
  • E. South Island
    South Island is a volcanic island located within Kenya’s Lake Turkana, known for its stark lava landscapes and rich bird and crocodile populations.
  • 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_69bd43d0497c8190ac23c65c5804846a completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd5a0374308190aeaffc9d866a3742 completed March 20, 2026, 2:30 p.m.
NED1 Entity disambiguation (via context triple) batch_69bdfa9b38f08190b7d96d9d72495cb9 completed March 21, 2026, 1:55 a.m.
Created at: March 20, 2026, 1:12 p.m.