Triple
T15476394
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 龍山寺 |
E376790
|
entity |
| Predicate | 奉祀神祇 |
P2291
|
FINISHED |
| Object | 關聖帝君 |
E213077
|
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: 關聖帝君 | Statement: [龍山寺, 奉祀神祇, 關聖帝君]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 關聖帝君 Context triple: [龍山寺, 奉祀神祇, 關聖帝君]
-
A.
Guandi
chosen
Guandi is a revered Chinese deity, often identified with the historical general Guan Yu, who is worshipped as a god of war, loyalty, and righteousness in Chinese folk religion and beyond.
-
B.
成湯
成湯 was the founding king of the Shang dynasty in ancient China, renowned for overthrowing the Xia dynasty and establishing a new royal order.
-
C.
義天玄承
義天玄承 was a Japanese Buddhist monk best known for founding the Zen temple Ryōan-ji in Kyoto, famous for its iconic rock garden.
-
D.
馬謖
馬謖 was a Shu Han military strategist and official of the Three Kingdoms period in China, best known for his failed command at the Battle of Jieting and the subsequent execution ordered by Zhuge Liang.
-
E.
仲達
仲達 is the courtesy name of Sima Yi, a prominent statesman and military strategist of the late Eastern Han and Three Kingdoms period who laid the foundations for the Jin dynasty in China.
- 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_69d85cd21dcc81908646251b1c26ea00 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e03f88a5dc8190a2d7830748e29180 |
completed | April 16, 2026, 1:46 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff2d093ccc8190aefc355a837c83f4 |
completed | May 9, 2026, 12:48 p.m. |
Created at: April 10, 2026, 3:34 a.m.