Triple
T21387714
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | He Guoqiang |
E527549
|
entity |
| Predicate | nativeName |
P15
|
FINISHED |
| Object | 贺国强 |
—
|
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: 贺国强 | Statement: [He Guoqiang, nativeName, 贺国强]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 贺国强 Context triple: [He Guoqiang, nativeName, 贺国强]
-
A.
陈庆炎
陈庆炎是新加坡前总统、资深政治家和前副总理，以在教育与经济发展领域的长期贡献而知名。
-
B.
Guo Shuqing
Guo Shuqing is a prominent Chinese economist and senior financial regulator who has held key positions overseeing China’s banking and insurance sectors.
-
C.
He Guoqiang
chosen
He Guoqiang is a retired Chinese politician who served on the Politburo Standing Committee of the Chinese Communist Party and headed its Central Commission for Discipline Inspection.
-
D.
Wang Qishan
Wang Qishan is a prominent Chinese politician best known for leading Xi Jinping’s sweeping anti-corruption campaign as head of the Communist Party’s top disciplinary body.
-
E.
康生
康生 was a powerful and notorious Chinese Communist Party leader and secret police chief, closely associated with Mao Zedong and major political purges during the mid-20th century.
- 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_69e0b51ff3748190935c0a513c62a12b |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69ee62cb05288190a894f33850e22c03 |
completed | April 26, 2026, 7:08 p.m. |
Created at: April 16, 2026, 5:12 p.m.