Triple
T18587984
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Brave One |
E454286
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Frank King |
—
|
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: Frank King | Statement: [The Brave One, producer, Frank King]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Frank King Context triple: [The Brave One, producer, Frank King]
-
A.
Frank King
Frank King is a computer scientist known for his key role in the development of IBM's pioneering System R relational database project.
-
B.
Frank King
chosen
Frank King is a film producer known for his work on the movie "The Party Crashers."
-
C.
Donald King
Donald King is a flamboyant and controversial American boxing promoter known for organizing some of the sport’s most famous heavyweight championship bouts.
-
D.
Donald King
Donald King was a member of the King family of Omaha, Nebraska, best known as the sibling of Leslie Lynch King Sr., the biological father of U.S. President Gerald Ford.
-
E.
Joe King
Joe King was an American actor active in early 20th-century cinema, appearing in numerous films during the silent and early sound eras.
- 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_69d8d38ae7e081908a98df1251842402 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e545b2f20481908da74447cd08d5bd |
completed | April 19, 2026, 9:14 p.m. |
Created at: April 10, 2026, 11:44 a.m.