Triple
T9806111
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Uji City |
E237957
|
entity |
| Predicate | hasLandmark |
P105
|
FINISHED |
| Object | Kosho-ji Temple |
E664615
|
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: Kosho-ji Temple | Statement: [Uji City, hasLandmark, Kosho-ji Temple]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kosho-ji Temple Context triple: [Uji City, hasLandmark, Kosho-ji Temple]
-
A.
Kōshō-ji Temple
chosen
Kōshō-ji Temple is a historic Japanese Buddhist temple notable for incorporating architectural materials from the former Fushimi Castle.
-
B.
Engyō-ji Temple
Engyō-ji Temple is an ancient Tendai Buddhist temple complex on Mount Shosha in Himeji, Japan, renowned for its historic wooden halls and scenic, forested setting.
-
C.
Seiganto-ji Temple
Seiganto-ji Temple is an ancient Buddhist temple in Wakayama Prefecture, Japan, famed for its picturesque pagoda standing before the dramatic Nachi Falls.
-
D.
Zenkō-ji Temple
Zenkō-ji Temple is a historic and highly revered Buddhist temple in Nagano, Japan, known as one of the country’s most important pilgrimage sites.
-
E.
Isshin-ji Temple
Isshin-ji Temple is a historic Buddhist temple in Osaka, Japan, renowned for its unique Buddha statues made from the cremated ashes of the deceased.
- 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_69ca84dd4608819097ff4ed00feca280 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdab7b67748190ba16ce868f29d13e |
completed | April 1, 2026, 11:34 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d9330fa33c8190b507ad18362a6c64 |
completed | April 10, 2026, 5:27 p.m. |
Created at: March 30, 2026, 8:29 p.m.