Triple
T7547951
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lee Teng-hui |
E178453
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Tseng Wen-hui |
E619886
|
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: Tseng Wen-hui | Statement: [Lee Teng-hui, spouse, Tseng Wen-hui]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tseng Wen-hui Context triple: [Lee Teng-hui, spouse, Tseng Wen-hui]
-
A.
Tseng Wen-hui
chosen
Tseng Wen-hui is a Taiwanese public figure best known as the wife of former President Lee Teng-hui and for serving as First Lady during Taiwan’s transition to democracy.
-
B.
Huang Jen-hsun
Huang Jen-hsun is a Taiwanese-American entrepreneur best known as the co-founder and longtime CEO of NVIDIA, a leading company in graphics processing and AI computing.
-
C.
Chiang Fang-liang
Chiang Fang-liang was the Belarusian-born wife of Chiang Ching-kuo and former First Lady of the Republic of China (Taiwan).
-
D.
Weng Wen-hao
Weng Wen-hao was a Chinese geologist and politician who briefly served as premier of the Republic of China during the late stages of the Chinese Civil War.
-
E.
Chen Po-wen
Chen Po-wen is a film editor best known for his work on the acclaimed Taiwanese historical war drama "Seediq Bale."
- 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_69c69f2cbe08819088f9eb0c03ef529b |
completed | March 27, 2026, 3:15 p.m. |
| NER | Named-entity recognition | batch_69c6f89b9afc8190b3e61a8e2cea7ad7 |
completed | March 27, 2026, 9:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c84f2b0de48190a854b4d4935c2254 |
completed | March 28, 2026, 9:59 p.m. |
Created at: March 27, 2026, 3:49 p.m.