Triple
T19717599
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Charles Kuen Kao |
E473519
|
entity |
| Predicate | nativeName |
P15
|
FINISHED |
| Object | 高錕 |
E108355
|
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: 高錕 | Statement: [Charles Kuen Kao, nativeName, 高錕]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 高錕 Context triple: [Charles Kuen Kao, nativeName, 高錕]
-
A.
高錕
chosen
高錕是一位华裔物理学家和电机工程师，被誉为“光纤之父”，因在光纤通信领域的开创性贡献而获得诺贝尔物理学奖。
-
B.
Teng Yu-kun
Teng Yu-kun is a Taiwanese film and television director and screenwriter known for his influential work in Mandarin-language cinema and TV dramas.
-
C.
Guo Guangchang
Guo Guangchang is a Chinese billionaire businessman and investor, best known as the chairman and co-founder of the Fosun Group conglomerate.
-
D.
Ricky Hui
Ricky Hui was a Hong Kong actor and comedian best known as a member of the Hui brothers and for his roles in classic 1980s horror-comedy films.
-
E.
Wu Yu-sen
Wu Yu-sen is the birth name of John Woo, the influential Hong Kong film director known for his stylized action cinema and "heroic bloodshed" genre.
- 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_69d8e516dd048190a0b6c93ea3e71f58 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6440ec9e881909b75c0ebefab827f |
completed | April 20, 2026, 3:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a07aba36954819085e53a67388086ab |
completed | May 15, 2026, 11:26 p.m. |
Created at: April 10, 2026, 1:46 p.m.