Triple
T20566580
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zisi |
E504979
|
entity |
| Predicate | associatedWork |
P922
|
FINISHED |
| Object | Zhongyong |
—
|
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: Zhongyong | Statement: [Zisi, associatedWork, Zhongyong]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Zhongyong Context triple: [Zisi, associatedWork, Zhongyong]
-
A.
Zhongyong
chosen
Zhongyong is a classical Confucian text that expounds the ideal of moral moderation, balance, and harmony as a central path to personal virtue and good governance.
-
B.
Mingzhe
Mingzhe is a given name associated with Peter Ma Mingzhe, a notable Chinese business figure and entrepreneur.
-
C.
Li Yi
Li Yi was a Tang dynasty imperial prince, notable as a son of Emperor Dezong of Tang.
-
D.
Qunti Zhong
Qunti Zhong is a traditional, locally adapted tea plant variety historically used to produce authentic Longjing (Dragon Well) green tea in China.
-
E.
Wei Jia
Wei Jia, better known by her posthumous title Empress Xiaoyichun, was a prominent Qing dynasty empress consort of the Qianlong Emperor and the mother of his successor, the Jiaqing Emperor.
- 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_69e0b4b6587c8190aee63dc7cff244ea |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6a7a33f7c8190966da03528dfe8aa |
completed | April 20, 2026, 10:24 p.m. |
Created at: April 16, 2026, 11:39 a.m.