Triple
T21193639
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frank Hsieh |
E522270
|
entity |
| Predicate | runningMate |
P1793
|
FINISHED |
| Object | Su Tseng-chang |
—
|
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: Su Tseng-chang | Statement: [Frank Hsieh, runningMate, Su Tseng-chang]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Su Tseng-chang Context triple: [Frank Hsieh, runningMate, Su Tseng-chang]
-
A.
Su Tseng-chang
chosen
Su Tseng-chang is a Taiwanese politician and senior member of the Democratic Progressive Party who has served multiple terms as premier and previously chaired the party.
-
B.
Chiang Hsiao-chang
Chiang Hsiao-chang is a Taiwanese figure best known as the daughter of former Republic of China President Chiang Ching-kuo and a member of the influential Chiang political family.
-
C.
Lu Shiow-yen
Lu Shiow-yen is a Taiwanese politician who serves as the mayor of Taichung, one of Taiwan’s largest cities.
-
D.
Teng Yu-shan
Teng Yu-shan is a Taiwanese film director and screenwriter known for her work in contemporary Taiwanese cinema.
-
E.
Tsai Chao-chu
Tsai Chao-chu is the wife of Taiwanese chemist and Nobel laureate Yuan T. Lee.
- 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_69e0b51061388190aa03f19700d3ef04 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e73339aaa081909d9009c58c386422 |
completed | April 21, 2026, 8:20 a.m. |
Created at: April 16, 2026, 3:08 p.m.