Triple
T4307803
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mao Zedong family |
E93997
|
entity |
| Predicate | hasChildOfPatriarch |
P6882
|
FINISHED |
| Object | Mao Anhong |
E442798
|
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 Anhong | Statement: [Mao Zedong family, hasChildOfPatriarch, Mao Anhong]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mao Anhong Context triple: [Mao Zedong family, hasChildOfPatriarch, Mao Anhong]
-
A.
Mao Anhong
chosen
Mao Anhong is a lesser-known son of Chinese Communist leader Mao Zedong and a member of the Mao family.
-
B.
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.
-
C.
Mao Xinyu
Mao Xinyu is a Chinese major general and military historian best known as the grandson of Mao Zedong.
-
D.
Yang Yuehua
Yang Yuehua is a Chinese individual known primarily for being the sibling of former professional tennis star Li Na.
-
E.
Wu Hong
Wu Hong is a Chinese art historian and curator renowned for his scholarship on traditional and contemporary Chinese art.
- 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_69b3563eab24819088add9180af2ce3c |
completed | March 13, 2026, 12:11 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b650abb8ec8190afb55dc0091f8415 |
completed | March 15, 2026, 6:24 a.m. |
Created at: March 12, 2026, 11:11 p.m.