Triple
T8760431
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | River Taw |
E208182
|
entity |
| Predicate | flowsThrough |
P225
|
FINISHED |
| Object | Newport, Barnstaple |
E492724
|
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: Newport, Barnstaple | Statement: [River Taw, flowsThrough, Newport, Barnstaple]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Newport, Barnstaple Context triple: [River Taw, flowsThrough, Newport, Barnstaple]
-
A.
Newport (Barnstaple)
chosen
Newport (Barnstaple) is a residential suburb of the town of Barnstaple in North Devon, England.
-
B.
Barnstaple
Barnstaple is a historic market town in North Devon, England, known as one of the region’s main commercial and service centers.
-
C.
Bridport
Bridport is a historic market town in southwest England known for its rope-making heritage and proximity to the Jurassic Coast.
-
D.
Truro
Truro is a town in central Nova Scotia, Canada, known historically as a key regional transportation hub and service center.
-
E.
Truro
Truro is a small coastal town on outer Cape Cod in Massachusetts known for its scenic beaches, dunes, and historic Highland Light lighthouse.
- 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_69ca835df7e08190ac875664cca8f9ca |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc5df9729481908679151988b76d2f |
completed | March 31, 2026, 11:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cf5197263881908038b5e2105e9170 |
completed | April 3, 2026, 5:35 a.m. |
Created at: March 30, 2026, 6:40 p.m.