Triple
T10937971
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thomas Shelby |
E258385
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Finn Shelby |
E258388
|
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: Finn Shelby | Statement: [Thomas Shelby, sibling, Finn Shelby]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Finn Shelby Context triple: [Thomas Shelby, sibling, Finn Shelby]
-
A.
Finn Shelby
chosen
Finn Shelby is the youngest member of the Shelby family in the British crime drama "Peaky Blinders," gradually drawn deeper into the gang's violent criminal world.
-
B.
Trevor Ford
Trevor Ford was a British geologist and paleontologist noted for his influential work on the fossils and geology of Charnwood Forest and the Peak District.
-
C.
Tim Fagan
Tim Fagan is a person notable enough to be recognized as a bearer of the surname Fagan, though specific widely known achievements or roles are not clearly established.
-
D.
Charles Ruthenberg
Charles Ruthenberg was an American socialist and communist political leader who played a key role in the early 20th-century U.S. radical labor and leftist movements.
-
E.
Jon DeVaan
Jon DeVaan is a longtime Microsoft engineering leader known for his key roles in developing and managing core Windows and Office technologies.
- 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_69d6aa8769b4819082bfe5e61b9017f0 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d770b12a9881909305db49aa554a1b |
completed | April 9, 2026, 9:26 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e3446b6f1481908365bb9235768859 |
completed | April 18, 2026, 8:44 a.m. |
Created at: April 8, 2026, 9:23 p.m.