Triple
T18380635
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kang Sheng |
E446432
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Kang Sheng |
—
|
NE NERFINISHED |
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: Kang Sheng | Statement: [Kang Sheng, name, Kang Sheng]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kang Sheng Context triple: [Kang Sheng, name, Kang Sheng]
-
A.
Kang Sheng
chosen
Kang Sheng was a prominent Chinese Communist Party leader and chief of Mao Zedong’s secret police, notorious for his role in political purges and the Cultural Revolution.
-
B.
Shi Xiangsheng
Shi Xiangsheng is a Chinese writer and screenwriter best known for creating the story and script for Zhang Yimou’s acclaimed film "Not One Less."
-
C.
Yang Dezhi
Yang Dezhi was a prominent Chinese general who held senior command roles in the People’s Liberation Army, including leadership during the Sino-Vietnamese War.
-
D.
Huang Kecheng
Huang Kecheng was a prominent Chinese Communist military leader and political figure who played key roles in the Chinese Civil War and later served in senior positions in the People’s Liberation Army and the government.
-
E.
Chung Shu-kun
Chung Shu-kun is a Hong Kong politician known for his involvement in local governance and public affairs.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b9f370b88190b1e5081c2c238e7f |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e5179aa328819097f5ed8193cfa401 |
completed | April 19, 2026, 5:57 p.m. |
Created at: April 10, 2026, 10:45 a.m.