Triple

T11840711
Position Surface form Disambiguated ID Type / Status
Subject Kondo (main hall) E281643 entity
Predicate partOf P40 FINISHED
Object To-ji E58823 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: To-ji | Statement: [Kondo (main hall), partOf, To-ji]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: To-ji
Context triple: [Kondo (main hall), partOf, To-ji]
  • A. To-ji chosen
    To-ji is a historic Buddhist temple in Kyoto, Japan, famed for its five-story pagoda—the tallest wooden tower in the country—and its status as a UNESCO World Heritage Site.
  • B. Shitenno-ji
    Shitenno-ji is one of Japan’s oldest Buddhist temples, founded in Osaka in the 6th century and renowned as a major historical and religious site.
  • C. Ryōzenji
    Ryōzenji is a Buddhist temple in Tokushima Prefecture, Japan, best known as the traditional starting point of the Shikoku 88-temple pilgrimage.
  • D. To-ji Temple
    To-ji Temple is a historic Buddhist temple in Kyoto, Japan, renowned for its five-story pagoda and its deep association with the monk Kobo Daishi and Shingon Buddhism.
  • E. Daigo-ji
    Daigo-ji is a historic Buddhist temple complex in Kyoto, Japan, renowned for its association with Shingon Buddhism, ancient pagoda, and UNESCO World Heritage status.
  • 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_69d6ab276f8c8190b1966a0ef11349ac completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d8a658f918819092c2db05fe2ab0ce completed April 10, 2026, 7:27 a.m.
NED1 Entity disambiguation (via context triple) batch_69f70a0e90e48190af6b802697d3256f completed May 3, 2026, 8:40 a.m.
Created at: April 8, 2026, 9:43 p.m.