Triple
T8530106
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Liu Shan |
E201922
|
entity |
| Predicate | reignTitle |
P10605
|
FINISHED |
| Object | Yanxi |
E695252
|
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: Yanxi | Statement: [Liu Shan, reignTitle, Yanxi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Yanxi Context triple: [Liu Shan, reignTitle, Yanxi]
-
A.
Yanxi
chosen
Yanxi was a regnal era of the Shu Han state during China’s Three Kingdoms period.
-
B.
Chongning
Chongning was a Chinese imperial era name used during the reign of Emperor Huizong of the Song dynasty.
-
C.
Wanrong
Wanrong was the last empress of China as the consort of Puyi, the final emperor of the Qing dynasty.
-
D.
Xiangmei
Xiangmei is the Chinese given name of Anna Chennault, a prominent Chinese-American journalist, author, and influential political figure in mid-20th-century U.S.-China relations.
-
E.
Princess Yangxin
Princess Yangxin was a Han dynasty imperial princess, known as a daughter of Emperor Jing of Han and a member of the Western Han royal family.
- 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_69ca83228b24819085d22e7dc99f5d94 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe67409f08190b20d13d26e9a362c |
completed | March 31, 2026, 3:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce6d68d14c81908bde8ca0113f9503 |
completed | April 2, 2026, 1:21 p.m. |
Created at: March 30, 2026, 6:17 p.m.