Triple
T9185313
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Devon Peninsula |
E220441
|
entity |
| Predicate | partOf |
P40
|
FINISHED |
| Object | county of Devon |
E100074
|
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: county of Devon | Statement: [Devon Peninsula, partOf, county of Devon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: county of Devon Context triple: [Devon Peninsula, partOf, county of Devon]
-
A.
West Devon
West Devon is a largely rural local government district and borough in the county of Devon, England, known for its moorland landscapes and historic market towns.
-
B.
ceremonial county of Devon
The ceremonial county of Devon is a historic and largely rural county in South West England, known for its rugged coastlines, national parks such as Dartmoor and Exmoor, and popular seaside resorts.
-
C.
Devon
Devon is a suburban community on the Philadelphia Main Line in Pennsylvania, best known for hosting the historic Devon Horse Show and Country Fair.
-
D.
Devon
chosen
Devon is a county in South West England known for its rugged coastlines, moorland national parks, and historic seaside towns.
-
E.
Devon
Devon is a residential neighbourhood located within the city of Fredericton in New Brunswick, Canada.
- 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_69ca83e6d77c81909862b7afef56b1bf |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69ccc318d5c081908c50b56e5783ea38 |
completed | April 1, 2026, 7:02 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d05c19635c81908ad2cf07f5ad813c |
completed | April 4, 2026, 12:32 a.m. |
Created at: March 30, 2026, 7:24 p.m.