Triple
T12057535
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 孫基禎 |
E287080
|
entity |
| Predicate | romanizedName |
P2508
|
FINISHED |
| Object | Son Kee-chung |
E287082
|
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: Son Kee-chung | Statement: [孫基禎, romanizedName, Son Kee-chung]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Son Kee-chung Context triple: [孫基禎, romanizedName, Son Kee-chung]
-
A.
Son Kee-chung
chosen
Son Kee-chung was a Korean marathon runner who won the gold medal at the 1936 Berlin Olympics while competing under the Japanese name Son Kitei during Japan’s colonial rule over Korea.
-
B.
Chin Han
Chin Han is a Singaporean actor known for his roles in major Hollywood films such as The Dark Knight, Contagion, and Skyscraper.
-
C.
Chan Kong-sang
Chan Kong-sang is the birth name of Jackie Chan, the internationally renowned Hong Kong martial artist, actor, stuntman, and filmmaker.
-
D.
Chow Po-chung
Chow Po-chung is a Hong Kong political theorist and academic known for his work on civic education, liberalism, and public policy.
-
E.
Yun Chi Chung
Yun Chi Chung is best known as the former wife of American comedian and actor Redd Foxx.
- 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_69d6ab4780948190bdb9f7620c2ac27e |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d9043bf0ec8190a51ef2641808320c |
completed | April 10, 2026, 2:07 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f49dea043c8190a74ffb448bbae5d0 |
completed | May 1, 2026, 12:34 p.m. |
Created at: April 8, 2026, 9:47 p.m.