Triple

T4874616
Position Surface form Disambiguated ID Type / Status
Subject Mount Haruna E109169 entity
Predicate hasShrine P15258 FINISHED
Object Haruna Shrine E512274 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: Haruna Shrine | Statement: [Mount Haruna, hasShrine, Haruna Shrine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Haruna Shrine
Context triple: [Mount Haruna, hasShrine, Haruna Shrine]
  • A. Haruna Shrine chosen
    Haruna Shrine is a historic Shinto shrine located on Mount Haruna in Gunma Prefecture, Japan, known for its scenic mountain setting and traditional architecture.
  • B. Hiromine Shrine
    Hiromine Shrine is a Shinto shrine in Japan dedicated to the storm god Susanoo, known for its traditional architecture and regional religious significance.
  • C. Nei Reei shrine
    Nei Reei shrine is a traditional religious site on the Kiribati island of Marakei, associated with local spiritual practices and ancestral worship.
  • D. Tsukiyomi Shrine
    Tsukiyomi Shrine is a Shinto shrine on Iki Island in Japan, dedicated to the moon deity Tsukuyomi and known as a historic spiritual site in the region.
  • E. Morito Shrine
    Morito Shrine is a historic Shinto shrine in the coastal town of Hayama, Kanagawa, known for its scenic seaside setting and views of Sagami Bay and Mount Fuji.
  • 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_69bd440d96a48190b0c87069adef2af1 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd6da1b45881909d45cb1214f5bdde completed March 20, 2026, 3:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf219bdd208190990db4b0fa89066a completed March 21, 2026, 10:54 p.m.
Created at: March 20, 2026, 1:27 p.m.