Triple
T28790790
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 賴清德 |
E726945
|
entity |
| Predicate | 前任中華民國總統 |
P28791
|
FINISHED |
| Object | 蔡英文 |
—
|
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: 蔡英文 | Statement: [賴清德, 前任中華民國總統, 蔡英文]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 前任中華民國總統 Context triple: [賴清德, 前任中華民國總統, 蔡英文]
-
A.
formerPresidentOf
Indicates that one entity previously held, but no longer holds, the official position of president of another entity.
-
B.
previousPresident
chosen
Indicates that one person held the office of president immediately before another person.
-
C.
lastPresident
Indicates that one entity is the most recent individual to have held the office of president of the other entity.
-
D.
officeEndTime (President of the Republic of China)
Indicates the time at which a President of the Republic of China’s term in office concludes.
-
E.
presidentElect
Indicates that one entity has been elected to be president of another entity (such as a country or organization) but has not yet assumed the office.
- F. None of above.
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_69f0319aabec81908368720196f69a35 |
completed | April 28, 2026, 4:03 a.m. |
| NER | Named-entity recognition | batch_69f658ee40088190b71e1219407690d0 |
completed | May 2, 2026, 8:05 p.m. |
| PD | Predicate disambiguation | batch_69f65760fd3081908ffe014a5e2bf069 |
completed | May 2, 2026, 7:58 p.m. |
Created at: April 28, 2026, 6:23 a.m.