Triple
T17589922
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 朱立倫 |
E428417
|
entity |
| Predicate | office |
P3103
|
FINISHED |
| Object | 中國國民黨主席 |
—
|
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: 中國國民黨主席 | Statement: [朱立倫, office, 中國國民黨主席]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 中國國民黨主席 Context triple: [朱立倫, office, 中國國民黨主席]
-
A.
Director-General of the Kuomintang
chosen
The Director-General of the Kuomintang is the top leadership position of Taiwan’s Kuomintang (KMT) party, historically associated with centralized authority over party policy, organization, and strategy.
-
B.
朱立倫
朱立倫 is a Taiwanese politician who has served as New Taipei City Mayor and Chairman of the Kuomintang (KMT).
-
C.
吳敦義
吳敦義是一位臺灣政治人物，曾任中華民國副總統及中國國民黨主席。
-
D.
賴清德
賴清德 is a Taiwanese politician who has served as president of the Republic of China (Taiwan) and is a leading figure in the Democratic Progressive Party.
-
E.
President of the Legislative Yuan
The President of the Legislative Yuan is the presiding officer and highest-ranking official of Taiwan’s unicameral legislature, responsible for overseeing its proceedings and administration.
- 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_69d889e1030481909950e140c63255b9 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e469e62d5c81909134e30a6d0f2e20 |
completed | April 19, 2026, 5:36 a.m. |
Created at: April 10, 2026, 5:51 a.m.