Triple
T23195034
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Imperial Commissioner |
E579849
|
entity |
| Predicate | notableHolder |
P1918
|
FINISHED |
| Object | Qishan |
—
|
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: Qishan | Statement: [Imperial Commissioner, notableHolder, Qishan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Qishan Context triple: [Imperial Commissioner, notableHolder, Qishan]
-
A.
Qishan
chosen
Qishan was a high-ranking Qing dynasty official and diplomat who played a key role in negotiating with the British during the First Opium War.
-
B.
Jiaoshan
Jiaoshan is a scenic island and historic site in the Yangtze River near Zhenjiang, known for its ancient temples, stone inscriptions, and natural beauty.
-
C.
Yishan
Yishan was a Qing dynasty military commander and noble who led Chinese forces during the First Opium War against Britain.
-
D.
Qianfoshan
Qianfoshan is a famous scenic mountain in Jinan, China, renowned for its numerous ancient Buddhist statues and temples.
-
E.
Zhuzihu
Zhuzihu is a scenic valley area in Taipei’s Yangmingshan National Park, best known for its cool-climate agriculture and seasonal calla lily fields.
- 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_69e24600eed08190bd7e5295653a1503 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18fda64cc8190aeb5ccd8d8d20858 |
completed | April 29, 2026, 4:58 a.m. |
Created at: April 17, 2026, 4:06 p.m.