Triple
T7135803
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tarka Line |
E166302
|
entity |
| Predicate | regionServed |
P82
|
FINISHED |
| Object | Barnstaple |
E114590
|
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: Barnstaple | Statement: [Tarka Line, regionServed, Barnstaple]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Barnstaple Context triple: [Tarka Line, regionServed, Barnstaple]
-
A.
Barnstaple
chosen
Barnstaple is a historic market town in North Devon, England, known as one of the region’s main commercial and service centers.
-
B.
Bideford
Bideford is a historic port town on the River Torridge in North Devon, England, known for its maritime heritage and role as a local commercial center.
-
C.
Paignton
Paignton is a seaside town in Devon, England, known for its sandy beaches, traditional pier, and role as part of the English Riviera resort area.
-
D.
Nailsea
Nailsea is a small town in North Somerset, England, historically known for its glassmaking and coal mining industries.
-
E.
Brixham
Brixham is a historic fishing town and port in Devon, England, known for its maritime heritage and role in traditional shipbuilding.
- 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_69c68884a9388190af42f90d1c1a7151 |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6e6926d748190bc8c150fc1860531 |
completed | March 27, 2026, 8:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7cbd551288190a53decc7021929ee |
completed | March 28, 2026, 12:38 p.m. |
Created at: March 27, 2026, 2:45 p.m.