Triple
T23098965
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fame (1980 film) |
E575972
|
entity |
| Predicate | stars |
P1956
|
FINISHED |
| Object | Barry Miller |
—
|
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: Barry Miller | Statement: [Fame (1980 film), stars, Barry Miller]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Barry Miller Context triple: [Fame (1980 film), stars, Barry Miller]
-
A.
Barry Miller
chosen
Barry Miller is an American actor best known for his roles in films like "Saturday Night Fever" and "Fame," as well as various television and stage productions.
-
B.
Barry Peters
Barry Peters is a film editor known for his work on the 1975 adaptation of "The Count of Monte Cristo."
-
C.
Darryl Miller
Darryl Miller is known primarily as the brother of Hall of Fame NBA shooting guard Reggie Miller.
-
D.
Mel Miller
Mel Miller is a central character in the 1957 film "A Face in the Crowd," serving as a thoughtful, morally grounded writer and producer who becomes increasingly disillusioned with the rise and corruption of media-made celebrity.
-
E.
Al Miller
Al Miller is an American soccer coach best known for his leadership roles with early North American professional teams, including the Dallas Tornado.
- 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_69e245c060b48190a9bd61a47a16db17 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18de71a088190b91918e6c4ea6e97 |
completed | April 29, 2026, 4:49 a.m. |
Created at: April 17, 2026, 3:58 p.m.