Triple
T22024761
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | To-in (Eastern Precinct of Horyu-ji) |
E543930
|
entity |
| Predicate | hasJapaneseName |
P9882
|
FINISHED |
| Object | 東院伽藍 |
—
|
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: 東院伽藍 | Statement: [To-in (Eastern Precinct of Horyu-ji), hasJapaneseName, 東院伽藍]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 東院伽藍 Context triple: [To-in (Eastern Precinct of Horyu-ji), hasJapaneseName, 東院伽藍]
-
A.
法華堂
法華堂（ほっけどう）は、奈良・東大寺境内にある奈良時代創建の仏堂で、国宝に指定された古式建築として知られる建造物である。
-
B.
金剛頂寺
金剛頂寺は、高知県室戸市に位置し、真言宗の寺院として四国八十八箇所霊場の第26番札所となっている古刹です。
-
C.
戒壇院
chosen
戒壇院 is a historic Buddhist ordination temple in Nara, Japan, traditionally associated with the formal conferral of monastic precepts.
-
D.
園城寺
園城寺 is a historic Tendai Buddhist temple complex in Ōtsu, Shiga Prefecture, Japan, renowned for its ancient halls, cultural treasures, and scenic setting near Lake Biwa.
-
E.
龍山寺
龍山寺 is a historic and culturally significant Buddhist temple in Taipei, Taiwan, renowned for its intricate architecture and role as a major religious and tourist landmark.
- 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_69e11e2e8ea4819084210fe06d3a1b8d |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f127ca45a08190b2d5d3a8eb37cb4b |
completed | April 28, 2026, 9:34 p.m. |
Created at: April 16, 2026, 8:23 p.m.