Triple
T4307782
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mao Zedong family |
E93997
|
entity |
| Predicate | notableMember |
P10
|
FINISHED |
| Object | He Zizhen |
E14743
|
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: He Zizhen | Statement: [Mao Zedong family, notableMember, He Zizhen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: He Zizhen Context triple: [Mao Zedong family, notableMember, He Zizhen]
-
A.
He Zizhen
chosen
He Zizhen was a Chinese revolutionary and early Communist Party member best known as one of Mao Zedong’s wives and a participant in the Long March.
-
B.
Zhu Yousong
Zhu Yousong was a Ming dynasty imperial prince who briefly reigned as the Hongguang Emperor, one of the Southern Ming claimants to the Chinese throne after the fall of Beijing to the Qing.
-
C.
Zhu Houxi
Zhu Houxi was a Ming dynasty imperial prince, known primarily as a son of the Hongzhi Emperor of China.
-
D.
Zhu Zaiji
Zhu Zaiji, better known as the Longqing Emperor, was a Ming dynasty ruler who briefly stabilized the empire and reopened trade after the tumultuous reign of his father, the Jiajing Emperor.
-
E.
Bai Chong Xi
Bai Chongxi was a prominent Chinese Muslim general and political figure of the Nationalist government during the first half of the 20th century.
- 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_69b3451886588190a3dd1305ea7c58dc |
completed | March 12, 2026, 10:58 p.m. |
| NER | Named-entity recognition | batch_69b350d2af088190ad7cb035d6e0f8c2 |
completed | March 12, 2026, 11:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b67ba3fef08190a0f92460703b0a98 |
completed | March 15, 2026, 9:28 a.m. |
Created at: March 12, 2026, 11:11 p.m.