Triple
T14171929
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tavistock Canal |
E351229
|
entity |
| Predicate | followsRiver |
P3624
|
FINISHED |
| Object | River Tavy |
E203593
|
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: River Tavy | Statement: [Tavistock Canal, followsRiver, River Tavy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: River Tavy Context triple: [Tavistock Canal, followsRiver, River Tavy]
-
A.
River Tavy
chosen
River Tavy is a river in Devon, England, that flows through the town of Tavistock before joining the River Tamar.
-
B.
River Teign
The River Teign is a river in Devon, England, that flows from Dartmoor to the English Channel and is known for its scenic valleys, wildlife, and historic bridges.
-
C.
River Taw
River Taw is a river in Devon, England, that flows through towns including Barnstaple before reaching the Bristol Channel.
-
D.
Lez River
The Lez River is a short coastal river in southern France that flows through the city of Montpellier before emptying into the Mediterranean Sea.
-
E.
River Whye
River Whye is a fictional river in Stephen King’s Dark Tower universe, flowing through the central realm known as Mid-World.
- 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_69d8278834a08190b0f1784e58d7b99c |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de61b5dcbc8190b0cfcce5e6c6d582 |
completed | April 14, 2026, 3:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fcf808e6088190a607903be0f2adc7 |
completed | May 7, 2026, 8:37 p.m. |
Created at: April 10, 2026, 1:01 a.m.