Triple
T15833822
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tai Jeng-wu |
E383935
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Tai Jeng-wu |
E383935
|
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: Tai Jeng-wu | Statement: [Tai Jeng-wu, name, Tai Jeng-wu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tai Jeng-wu Context triple: [Tai Jeng-wu, name, Tai Jeng-wu]
-
A.
Tai Jeng-wu
chosen
Tai Jeng-wu is a Taiwanese business executive best known for leading Sharp Corporation’s turnaround as its president.
-
B.
Teng Yu-lung
Teng Yu-lung is an individual notable for bearing the Chinese surname Teng, though specific widely recognized public achievements or roles are not well documented.
-
C.
Chiu Chui-cheng
Chiu Chui-cheng is a Taiwanese politician who has served in senior roles related to cross-strait relations and policy toward mainland China.
-
D.
Lin Ching-tai
Lin Ching-tai is an actor best known for his role in the Taiwanese historical epic film "Seediq Bale," which depicts the indigenous Seediq people's resistance against Japanese rule.
-
E.
Teng Yu-chuan
Teng Yu-chuan is a person notable for bearing the Chinese surname Teng, though specific widely known biographical or professional details about them are not well documented in major public sources.
- 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_69d86da34c888190976e06c4019d415a |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e11e6670d48190a456581dd951f168 |
completed | April 16, 2026, 5:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fff79031f88190bf129582deeed3b9 |
completed | May 10, 2026, 3:12 a.m. |
Created at: April 10, 2026, 4:49 a.m.