Triple
T23152772
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hard Candy |
E578363
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | Brian Nelson |
—
|
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: Brian Nelson | Statement: [Hard Candy, screenwriter, Brian Nelson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Brian Nelson Context triple: [Hard Candy, screenwriter, Brian Nelson]
-
A.
Brian Nelson
chosen
Brian Nelson is an American screenwriter best known for his work on the horror film "30 Days of Night" and the thriller "Hard Candy."
-
B.
Kent Nelson
Kent Nelson is the DC Comics sorcerer who becomes Doctor Fate, a powerful mystical hero and longtime member of the Justice Society of America.
-
C.
Ken Nelson
Ken Nelson is a British record producer best known for his work with Coldplay, including producing their hit song "Fix You."
-
D.
Ken Nelson
Ken Nelson was an influential American record producer best known for his work with country and pop artists at Capitol Records during the mid-20th century.
-
E.
Jack Nelson
Jack Nelson was an early 20th-century American actor known for his roles in silent films.
- 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_69e245fb8de081908f0eba7b5fd75bc4 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18efaa1fc81908fb1987dbf732f46 |
completed | April 29, 2026, 4:54 a.m. |
Created at: April 17, 2026, 4:01 p.m.