Triple
T4734854
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mao Anlong |
E105098
|
entity |
| Predicate | notableRelative |
P367
|
FINISHED |
| Object | Mao Yuanxin |
E108807
|
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: Mao Yuanxin | Statement: [Mao Anlong, notableRelative, Mao Yuanxin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mao Yuanxin Context triple: [Mao Anlong, notableRelative, Mao Yuanxin]
-
A.
Mao Yuanxin
chosen
Mao Yuanxin is a Chinese political figure known as Mao Zedong’s nephew who briefly held influential positions during the final years of the Cultural Revolution.
-
B.
Mao Yichang
Mao Yichang was the father of Mao Zedong and a relatively prosperous peasant farmer in Hunan, China.
-
C.
Lu Muzhen
Lu Muzhen was the first wife of Chinese revolutionary leader Sun Yat-sen, known primarily for her connection to his early life and career.
-
D.
Liu Xianshi
Liu Xianshi was a Chinese military and political figure from Yunnan who rose to prominence as a warlord during the early Republican era.
-
E.
Mao Anqing
Mao Anqing was the second son of Chinese Communist leader Mao Zedong, known for his work as a Russian-language translator and his relatively low political profile compared to his father.
- 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_69bd43ee52048190b81a4f066534ffb3 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd648148b48190ae30631115339ba1 |
completed | March 20, 2026, 3:15 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bfdb12f33c819084d9268bd31b1f6c |
completed | March 22, 2026, 12:05 p.m. |
Created at: March 20, 2026, 1:19 p.m.