Triple
T20584041
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nigatsu-dō |
E505736
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Nigatsu-dō |
—
|
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: Nigatsu-dō | Statement: [Nigatsu-dō, name, Nigatsu-dō]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nigatsu-dō Context triple: [Nigatsu-dō, name, Nigatsu-dō]
-
A.
Nigatsu-dō
chosen
Nigatsu-dō is a prominent sub-temple hall within the Tōdai-ji complex in Nara, Japan, renowned for its annual Shuni-e (Omizutori) Buddhist repentance ceremony.
-
B.
Yoshida Shrine
Yoshida Shrine is a historic Shinto shrine in Kyoto, Japan, known for its association with the influential Yoshida family and its role in the development of Shinto theology.
-
C.
Daikō-ji
Daikō-ji is a Buddhist temple in Japan known as Temple 67 on the Shikoku Pilgrimage route.
-
D.
Kōtoku-in
Kōtoku-in is a Buddhist temple in Kamakura, Japan, best known for its monumental outdoor bronze statue of the Great Buddha (Daibutsu).
-
E.
Pujiu Temple
Pujiu Temple is a historic Buddhist temple near Yuncheng in Shanxi, China, renowned for its ancient architecture and association with classic Chinese literature.
- 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_69e0b4b9669c8190b8e81fc72817d42c |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6a974ee4c819099310b46885a5597 |
completed | April 20, 2026, 10:32 p.m. |
Created at: April 16, 2026, 11:40 a.m.