Triple
T20494833
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kondō (Tōshōdai-ji) |
E502842
|
entity |
| Predicate | hasJapaneseName |
P9882
|
FINISHED |
| Object | 金堂 |
—
|
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: 金堂 | Statement: [Kondō (Tōshōdai-ji), hasJapaneseName, 金堂]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 金堂 Context triple: [Kondō (Tōshōdai-ji), hasJapaneseName, 金堂]
-
A.
金堂
chosen
金堂 is the main hall of Yakushi-ji Temple in Nara, Japan, renowned as an important example of classical Buddhist temple architecture.
-
B.
Shuangliu District
Shuangliu District is an urban district of Chengdu, China, known as a major transportation hub and home to one of the country’s busiest international airports.
-
C.
Zengdu District
Zengdu District is an urban administrative district of Suizhou City in Hubei Province, China, serving as one of its key political and economic centers.
-
D.
Luojiang District
Luojiang District is an administrative district of Quanzhou in Fujian Province, China, known for its mix of urban development and traditional coastal communities.
-
E.
黄陂
黄陂是中国湖北省武汉市下辖的一个区，位于长江中游北岸，以其悠久历史和城乡结合的区域特征而闻名。
- 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_69e0b4b0373881909dd3e9387f82eab4 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e69cbd2dfc81908204f7bfa8a763b6 |
completed | April 20, 2026, 9:38 p.m. |
Created at: April 16, 2026, 11:35 a.m.