Triple
T19183204
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Emperor Yang of Sui |
E469629
|
entity |
| Predicate | deathPlace |
P21
|
FINISHED |
| Object | Jiangdu |
—
|
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: Jiangdu | Statement: [Emperor Yang of Sui, deathPlace, Jiangdu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jiangdu Context triple: [Emperor Yang of Sui, deathPlace, Jiangdu]
-
A.
Yangzhou
chosen
Yangzhou is a historic city in eastern China renowned for its canals, gardens, and role as a major cultural and commercial center along the Grand Canal.
-
B.
Zhenjiang
Zhenjiang is a historic port city in eastern China known for its strategic location on the Yangtze River and its rich cultural and culinary heritage.
-
C.
Jingjiang
Jingjiang is a county-level city in Jiangsu Province, China, situated along the Yangtze River and known for its river port and industrial economy.
-
D.
Huangzhou
Huangzhou is the central urban district and administrative heart of Huanggang in Hubei Province, China.
-
E.
Huangwu
Huangwu was a regnal era title used by Sun Quan, the founding emperor of Eastern Wu during China’s Three Kingdoms period.
- 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_69d8dd09d5a081909ae43c286651ae5a |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5f61e1c248190ba9e220c1be61ef8 |
completed | April 20, 2026, 9:47 a.m. |
Created at: April 10, 2026, 12:07 p.m.