Triple
T4273967
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Liu Songlin |
E97002
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Mao Anqing |
E16414
|
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 Anqing | Statement: [Liu Songlin, spouse, Mao Anqing]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mao Anqing Context triple: [Liu Songlin, spouse, Mao Anqing]
-
A.
Mao Anqing
chosen
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.
-
B.
Mao Anying
Mao Anying was the eldest son of Chinese leader Mao Zedong, best known for his death while serving as a volunteer officer in the Korean War.
-
C.
Mao Yuanxin
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.
-
D.
Mao Anhong
Mao Anhong is a lesser-known son of Chinese Communist leader Mao Zedong and a member of the Mao family.
-
E.
Deng Hua
Deng Hua was a prominent Chinese military commander and general in the People's Volunteer Army during the Korean War.
- 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_69b34544be3c819084d1ab82d29f90c5 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b3501abb74819086b2f04ac7a5c114 |
completed | March 12, 2026, 11:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b63734dee08190a9c0e051a28d9177 |
completed | March 15, 2026, 4:36 a.m. |
Created at: March 12, 2026, 11:07 p.m.