Triple
T22255204
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Anton Corbijn |
E550078
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Control |
—
|
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: Control | Statement: [Anton Corbijn, notableWork, Control]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Control Context triple: [Anton Corbijn, notableWork, Control]
-
A.
Control
"Control" is the second studio album by American pop group Dream Street, showcasing their teen pop sound in the early 2000s.
-
B.
Control
chosen
Control is a 2007 black-and-white biographical film directed by Anton Corbijn that portrays the life and tragic death of Joy Division frontman Ian Curtis.
-
C.
Control
Control is a critically acclaimed third-person action-adventure video game known for its surreal narrative, paranormal abilities, and striking brutalist setting.
-
D.
Control
Control is a competitive objective-based multiplayer game mode in Call of Duty where teams alternate between attacking and defending limited capture points with a shared pool of lives.
-
E.
Control
"Control" is a song by the American R&B singer Empress.
- 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_69e11e42adb8819087714772ea606709 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f138c1d70881908df47b0f818c0022 |
completed | April 28, 2026, 10:46 p.m. |
Created at: April 16, 2026, 8:39 p.m.