Triple
T21150494
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sun Yun-suan |
E521173
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Sun Yun-suan |
—
|
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: Sun Yun-suan | Statement: [Sun Yun-suan, name, Sun Yun-suan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sun Yun-suan Context triple: [Sun Yun-suan, name, Sun Yun-suan]
-
A.
Sun Yun-suan
chosen
Sun Yun-suan was a Taiwanese engineer-turned-statesman widely credited with spearheading Taiwan’s rapid industrialization and economic transformation in the 1970s and early 1980s.
-
B.
Go Yeong-nang
Go Yeong-nang is the birth name of King Jangsu, a prominent ruler of the ancient Korean kingdom of Goguryeo known for greatly expanding its territory and influence.
-
C.
Son Ki-jung
Son Ki-jung was a Korean marathon runner who won the gold medal at the 1936 Berlin Olympics while competing for Japan under the name Son Kee-chung.
-
D.
Wang Ryung
Wang Ryung was a late Silla-period nobleman and regional power whose son Wang Geon (Taejo of Goryeo) founded the Goryeo dynasty in Korea.
-
E.
Chun Lee-kyung
Chun Lee-kyung is a South Korean former short track speed skater and multiple Olympic gold medalist who dominated women’s events in the 1990s.
- 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_69e0b50c6a848190a4e525a77a319b8a |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e72400911c8190978e88138a9bfaff |
completed | April 21, 2026, 7:15 a.m. |
Created at: April 16, 2026, 2:58 p.m.