Triple
T17999727
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zhu Guangya |
E430594
|
entity |
| Predicate | nativeName |
P15
|
FINISHED |
| Object | 朱光亚 |
—
|
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: 朱光亚 | Statement: [Zhu Guangya, nativeName, 朱光亚]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 朱光亚 Context triple: [Zhu Guangya, nativeName, 朱光亚]
-
A.
吴大观
吴大观是中国著名航空发动机专家和教育家，被誉为中国航空发动机事业的重要奠基人之一。
-
B.
Deng Jiaxian
Deng Jiaxian was a leading Chinese nuclear physicist known as one of the principal architects of China’s atomic and hydrogen bomb programs.
-
C.
Zhu Guangya
chosen
Zhu Guangya was a prominent Chinese nuclear physicist and key architect of China’s nuclear weapons and energy programs.
-
D.
Peng Shilu
Peng Shilu was a pioneering Chinese nuclear engineer widely regarded as the "father of China's nuclear submarines" for his leading role in developing the country's first nuclear-powered subs.
-
E.
包信和
包信和 is a prominent Chinese physical chemist and academician of the Chinese Academy of Sciences known for his research in catalysis and energy chemistry.
- 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_69d8b90364248190a37381adea932f42 |
completed | April 10, 2026, 8:46 a.m. |
| NER | Named-entity recognition | batch_69e4b3e75e908190a6ff6a3ec6069ff5 |
completed | April 19, 2026, 10:52 a.m. |
Created at: April 10, 2026, 10:23 a.m.