Triple
T5623960
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roman Coppola |
E147674
|
entity |
| Predicate | relative |
P37
|
FINISHED |
| Object | Nicolas Cage |
E108795
|
NE FINISHED |
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: Nicolas Cage | Statement: [Roman Coppola, relative, Nicolas Cage]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nicolas Cage Context triple: [Roman Coppola, relative, Nicolas Cage]
-
A.
Nicolas Cage
chosen
Nicolas Cage is an American actor known for his intense and eclectic performances across action, drama, and independent films.
-
B.
Val Kilmer
Val Kilmer is an American actor known for his versatile performances in films such as "Top Gun," "The Doors," and "Batman Forever."
-
C.
Edward Norton
Edward Norton is an acclaimed American actor and filmmaker known for his intense, nuanced performances in films such as "Fight Club," "American History X," and "Birdman."
-
D.
Thomas Jane
Thomas Jane is an American actor best known for his roles in films such as "The Punisher," "Deep Blue Sea," and "Boogie Nights," as well as the TV series "The Expanse."
-
E.
Anthony Redman
Anthony Redman is a film editor best known for his work on the 1990 crime drama "King of New York."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69c00906f2a88190a992c66b13d606d4 |
completed | March 22, 2026, 3:21 p.m. |
| NER | Named-entity recognition | batch_69c022165d8c8190b2a14f1cd0a45ecc |
completed | March 22, 2026, 5:08 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c04d6180f081908145f8d70ad6434c |
completed | March 22, 2026, 8:13 p.m. |
Created at: March 22, 2026, 3:40 p.m.