Triple
T34157215
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | George Shelby |
E876170
|
entity |
| Predicate | instanceOf |
P0
|
FINISHED |
| Object | Peaky Blinders character |
C59854
|
CONCEPT FINISHED |
How this triple was built (1 step)
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.
CD
Concept disambiguation
gpt-5-mini-2025-08-07
Target class: Peaky Blinders character Context triple: [George Shelby, instanceOf, Peaky Blinders character]
-
A.
Peaky Blinders character
chosen
A Peaky Blinders character is a fictional individual from the gritty, early 20th-century Birmingham underworld, defined by complex moral ambiguity, sharp style, and involvement in crime, family loyalty, and power struggles.
-
B.
Downton Abbey character
A Downton Abbey character is an individual—whether aristocrat, servant, or outsider—whose personal story, relationships, and social role intertwine within the early 20th-century English estate of Downton Abbey.
-
C.
Kingsman character
A Kingsman character is a highly skilled, impeccably dressed secret agent belonging to an elite, independent intelligence organization that operates under the guise of a traditional British tailor shop.
-
D.
Torchwood character
A Torchwood character is an individual—human, alien, or otherwise—who plays a role in the secretive, extraterrestrial-investigating Torchwood Institute universe, contributing to its stories of covert operations, moral ambiguity, and encounters with the unknown.
-
E.
Game of Thrones character
A Game of Thrones character is a fictional individual within the A Song of Ice and Fire universe whose personal ambitions, loyalties, and moral complexities drive and reflect the series’ intricate political and social conflicts.
- F. None of above.
Provenance (1 batch)
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_69f349ac987481908a8e6053f665bc8b |
completed | April 30, 2026, 12:23 p.m. |
Created at: May 1, 2026, 1:54 a.m.