Triple

T15759560
Position Surface form Disambiguated ID Type / Status
Subject Mount Victoria Lookout E382058 entity
Predicate nearbySettlement P350 FINISHED
Object Mount Victoria E78575 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: Mount Victoria | Statement: [Mount Victoria Lookout, nearbySettlement, Mount Victoria]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mount Victoria
Context triple: [Mount Victoria Lookout, nearbySettlement, Mount Victoria]
  • A. Mount Victoria chosen
    Mount Victoria is a small historic village and mountain locality at the western edge of the Blue Mountains in New South Wales, Australia, known for its heritage architecture and scenic views.
  • B. Mount Victoria
    Mount Victoria is a prominent peak in western Myanmar known for its biodiversity-rich forests and panoramic views within the Chin Hills region.
  • C. Mount Victoria
    Mount Victoria is the former name of Mount Tomanivi, the highest peak in Fiji located on the island of Viti Levu.
  • D. Mount Paterson
    Mount Paterson is a mountain peak in the Allardyce Range on the sub-Antarctic island of South Georgia, known for its rugged, glaciated terrain.
  • E. Mount Herbert
    Mount Herbert is the tallest peak on New Zealand’s Banks Peninsula, known for its panoramic views over the Canterbury region and popular hiking routes.
  • 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_69d86d9e6b44819085d1f6a969ecb74c completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e050b35ea48190a758ee76a57b5451 completed April 16, 2026, 3 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff8774eda08190a6231b4fd5027e6f completed May 9, 2026, 7:13 p.m.
Created at: April 10, 2026, 4:47 a.m.