Triple
T15089161
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Temple 13: Dainichiji |
E360366
|
entity |
| Predicate | hasJapaneseName |
P9882
|
FINISHED |
| Object | 大日寺 |
E1093110
|
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: 大日寺 | Statement: [Temple 13: Dainichiji, hasJapaneseName, 大日寺]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 大日寺 Context triple: [Temple 13: Dainichiji, hasJapaneseName, 大日寺]
-
A.
大日寺
chosen
大日寺 is a Buddhist temple in Japan known as the fourth stop on the Shikoku 88-temple pilgrimage.
-
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.
白峯寺
白峯寺 is a historic Buddhist temple in Kagawa Prefecture, Japan, known as Temple 81 on the Shikoku Pilgrimage.
-
D.
仁和寺
仁和寺（Ninna-ji） is a historic Buddhist temple in Kyoto, Japan, renowned as a former imperial monastery and a UNESCO World Heritage Site noted for its classical architecture and gardens.
-
E.
Baima Temple
Baima Temple is an ancient Buddhist temple in Luoyang, China, widely regarded as the first officially established Buddhist temple in the country and a key cradle of Chinese Buddhism.
- 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_69d85a035aa88190b52a139d3a1b7b6d |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e00277ea808190be3f002a8316eff1 |
completed | April 15, 2026, 9:26 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69feae1ba4208190b1e8c55668a1b422 |
completed | May 9, 2026, 3:46 a.m. |
Created at: April 10, 2026, 3:04 a.m.