Triple
T10624445
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Evergreen Marine |
E250285
|
entity |
| Predicate | founder |
P104
|
FINISHED |
| Object | Chang Yung-fa |
E270917
|
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: Chang Yung-fa | Statement: [Evergreen Marine, founder, Chang Yung-fa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Chang Yung-fa Context triple: [Evergreen Marine, founder, Chang Yung-fa]
-
A.
Chang Yung-fa
chosen
Chang Yung-fa was a Taiwanese shipping magnate and philanthropist best known as the billionaire founder of the Evergreen Group conglomerate.
-
B.
Wu Chih-yang
Wu Chih-yang is a Taiwanese politician and public figure known primarily as the son of former Kuomintang chairman Wu Po-hsiung.
-
C.
Hsu Yung-chang
Hsu Yung-chang was a Chinese military representative who took part in formalizing Japan’s World War II surrender by signing the Japanese Instrument of Surrender.
-
D.
Huang Chih-ming
Huang Chih-ming is a Taiwanese film producer best known for his work on the historical epic "Seediq Bale."
-
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 (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_69d6aa5993448190a493b790b8f85010 |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d6df7fe9fc81908b3b8d1dc06a829c |
completed | April 8, 2026, 11:06 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d988474cf0819087516026fd249640 |
completed | April 10, 2026, 11:31 p.m. |
Created at: April 8, 2026, 8:53 p.m.