Triple
T18830672
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Road to Reno |
E460518
|
entity |
| Predicate | stars |
P1956
|
FINISHED |
| Object | John Miljan |
—
|
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: John Miljan | Statement: [The Road to Reno, stars, John Miljan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Miljan Context triple: [The Road to Reno, stars, John Miljan]
-
A.
John Miljan
chosen
John Miljan was an American film actor known for his prolific career in early Hollywood, often portraying suave villains and authority figures in silent and sound films.
-
B.
John Milarky
John Milarky is a musician known for being a member of the Scottish rock band Simple Minds.
-
C.
George Kralovansky
George Kralovansky is a television producer best known for his executive production work on the live law-enforcement reality series "Live PD."
-
D.
Kevin Pavlovic
Kevin Pavlovic is a film editor known for his work on the animated comedy feature "Sausage Party."
-
E.
Michael Kuzak
Michael Kuzak is a central attorney character on the television legal drama "L.A. Law," known for his idealism and high-profile courtroom battles.
- 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_69d8dcf94c288190a06dea029ae4b223 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5a9992bb081908ba517a5c9d93ef3 |
completed | April 20, 2026, 4:20 a.m. |
Created at: April 10, 2026, 11:56 a.m.