Triple
T22628009
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | A Shot in the Dark |
E558475
|
entity |
| Predicate | stars |
P1956
|
FINISHED |
| Object | Burt Kwouk |
—
|
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: Burt Kwouk | Statement: [A Shot in the Dark, stars, Burt Kwouk]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Burt Kwouk Context triple: [A Shot in the Dark, stars, Burt Kwouk]
-
A.
Burt Kwouk
chosen
Burt Kwouk was a British actor best known for his comedic role as Cato Fong in the Pink Panther film series.
-
B.
Herb Wong
Herb Wong is a jazz educator, producer, and longtime radio broadcaster known for his influential role in promoting and documenting West Coast jazz.
-
C.
James Kwong
James Kwong is a singer and performer best known as a later member of the disco group Village People.
-
D.
Eddie Wu
Eddie Wu is a Chinese entrepreneur and technology executive best known as a co-founder and later CEO of Alibaba Group.
-
E.
Victor Sen Yung
Victor Sen Yung was a Chinese American character actor best known for his roles as Hop Sing on the television series "Bonanza" and as Jimmy Chan in the Charlie Chan film series.
- 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_69e245467d9881908d6985bd0db7a1f1 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f16e3ed1d48190a093013d829901b9 |
completed | April 29, 2026, 2:34 a.m. |
Created at: April 17, 2026, 3:02 p.m.