Triple
T4273968
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mao Anqing |
E97002
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Liu Songlin |
E97002
|
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: Liu Songlin | Statement: [Mao Anqing, spouse, Liu Songlin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Liu Songlin Context triple: [Mao Anqing, spouse, Liu Songlin]
-
A.
Liu Songlin
chosen
Liu Songlin was the wife of Mao Anqing, the second son of Chinese Communist leader Mao Zedong.
-
B.
Chen Yongren
Chen Yongren is the undercover police officer protagonist of the Hong Kong crime thriller "Infernal Affairs," whose character later inspired Billy Costigan in the American remake "The Departed."
-
C.
Jin Liqun
Jin Liqun is a Chinese politician and banker who became the founding president of the Asian Infrastructure Investment Bank, playing a key role in shaping its strategy and global profile.
-
D.
Peng Huanwu
Peng Huanwu was a prominent Chinese theoretical physicist known for his contributions to nuclear and particle physics and for helping advance modern physics research in China.
-
E.
Ye Zhengguang
Ye Zhengguang is a descendant of prominent Chinese military leader and politician Ye Ting.
- 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_69b5c71fc0bc8190922ae85d3bd23546 |
completed | March 14, 2026, 8:37 p.m. |
Created at: March 12, 2026, 11:07 p.m.