Triple
T18710013
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Kapelos |
E457480
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Miami Vice |
—
|
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: Miami Vice | Statement: [John Kapelos, notableWork, Miami Vice]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Miami Vice Context triple: [John Kapelos, notableWork, Miami Vice]
-
A.
Miami Vice
chosen
Miami Vice is a 1980s American television crime drama series known for its stylish depiction of undercover detectives in Miami, distinctive fashion, and influential use of contemporary music.
-
B.
Moon Over Miami
Moon Over Miami is a 1941 Technicolor musical comedy film best known for starring Betty Grable in one of her signature early screen roles.
-
C.
Low Rider
"Low Rider" is a classic 1975 funk-rock song by the band War, known for its distinctive bassline and association with Chicano car culture.
-
D.
Stranger in Paradise
"Stranger in Paradise" is a popular song closely associated with Tony Bennett, adapted from Alexander Borodin's music and featured in the musical *Kismet*.
-
E.
Be Cool
"Be Cool" is a song featured on the album *Travelogue*, likely known as one of its notable tracks.
- 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_69d8d392aad081909fe31aa03e6e97d1 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e5671a3c8c81909466bf5d81477a37 |
completed | April 19, 2026, 11:36 p.m. |
Created at: April 10, 2026, 11:50 a.m.