Triple

T19682695
Position Surface form Disambiguated ID Type / Status
Subject Hossō school E472631 entity
Predicate importantTemple P13905 FINISHED
Object Yakushi-ji 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: Yakushi-ji | Statement: [Hossō school, importantTemple, Yakushi-ji]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Yakushi-ji
Context triple: [Hossō school, importantTemple, Yakushi-ji]
  • A. Yakushi-ji chosen
    Yakushi-ji is a major Buddhist temple in Nara, Japan, renowned as one of the country’s oldest and most important historic and architectural sites.
  • B. Shokoku-ji Temple
    Shokoku-ji Temple is a major Rinzai Zen Buddhist temple in Kyoto, Japan, renowned as one of the city's historically significant "Five Great Zen Temples."
  • C. Tōshōdai-ji
    Tōshōdai-ji is an 8th-century Buddhist temple in Nara, Japan, renowned for its well-preserved classical architecture and association with the Chinese monk Jianzhen (Ganjin).
  • D. Kanzeon-ji
    Kanzeon-ji is an ancient Buddhist temple in Dazaifu, Japan, historically significant as a major religious and cultural center of the region.
  • E. Hozenji Temple
    Hozenji Temple is a small, historic Buddhist temple in Osaka’s Namba district, famed for its moss-covered Fudō Myōō statue that visitors splash with water for good fortune.
  • 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_69d8e514f2e08190ba70a4449519d218 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e641c126b88190820281058a1e7793 completed April 20, 2026, 3:09 p.m.
Created at: April 10, 2026, 1:45 p.m.