Triple
T21872828
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roger Dean |
E540050
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Roger Dean |
—
|
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: Roger Dean | Statement: [Roger Dean, name, Roger Dean]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Roger Dean Context triple: [Roger Dean, name, Roger Dean]
-
A.
Roger Dean
chosen
Roger Dean is a British artist and designer renowned for his distinctive, surreal album cover art, particularly for progressive rock bands like Yes.
-
B.
Bernie Wrightson
Bernie Wrightson was an American artist renowned for his highly detailed horror and fantasy illustrations, particularly his work on Swamp Thing and his illustrated edition of Mary Shelley’s Frankenstein.
-
C.
Frank Frazetta
Frank Frazetta was an influential American fantasy and science fiction artist renowned for his dynamic, muscular figures and iconic book and album cover illustrations.
-
D.
Roy Heath
Roy Heath was a Guyanese-born British novelist and lawyer best known for his psychologically rich portrayals of Guyanese life and the immigrant experience.
-
E.
Robert Kessel
Robert Kessel is a film producer best known for his work on the drama movie "Proof."
- 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_69e0c478f59081909d54302b57fc1ce3 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f0f337ab5c8190937a457d348c732b |
completed | April 28, 2026, 5:49 p.m. |
Created at: April 16, 2026, 7 p.m.