Triple
T20807094
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Finishing the Game |
E512191
|
entity |
| Predicate | stars |
P1956
|
FINISHED |
| Object | Sung Kang |
—
|
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: Sung Kang | Statement: [Finishing the Game, stars, Sung Kang]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sung Kang Context triple: [Finishing the Game, stars, Sung Kang]
-
A.
Sung Kang
chosen
Sung Kang is an American actor best known for his role as Han Lue in the Fast & Furious film franchise.
-
B.
Tom Jung
Tom Jung is an American illustrator and film poster artist renowned for creating iconic artwork for major movies and novels, including the cover art for "Dark Force Rising."
-
C.
Il-woo Jung
Il-woo Jung is a Korean individual notable enough to be recognized as a prominent bearer of the surname Jung.
-
D.
Lewis Taewan Kim
Lewis Taewan Kim is a film producer best known for his work on the critically acclaimed fantasy drama film "Okja."
-
E.
John Cho
John Cho is a Korean American actor best known for his roles in the "Harold & Kumar" comedy series and as Hikaru Sulu in the rebooted "Star Trek" film franchise.
- 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_69e0b4cc69f481908e98751e697b9df4 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c2cfdee481908e42a1a8940ea40c |
completed | April 21, 2026, 12:20 a.m. |
Created at: April 16, 2026, 12:40 p.m.