Triple
T1161759
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | River Leven (Fife) |
E24507
|
entity |
| Predicate | hasMouthNear |
P350
|
FINISHED |
| Object | Methil |
E9837
|
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: Methil | Statement: [River Leven (Fife), hasMouthNear, Methil]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Methil Context triple: [River Leven (Fife), hasMouthNear, Methil]
-
A.
Methil
chosen
Methil is a coastal town in eastern Scotland that forms part of the Levenmouth area on the Firth of Forth.
-
B.
Vannin
Vannin is the Manx name for the Isle of Man, a self-governing British Crown dependency in the Irish Sea.
-
C.
The Wash
The Wash is a large square-mouthed bay and estuary on the east coast of England, where several rivers meet the North Sea and which forms a natural boundary between Lincolnshire and Norfolk.
-
D.
Shoreline
Shoreline is a suburban city in Washington State located just north of Seattle, known for its residential neighborhoods, parks, and access to Puget Sound.
-
E.
Orne
Orne is a rural department in northwestern France known for its pastoral landscapes, horse breeding, and historic towns such as Alençon.
- 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_69a494060e148190abb42f971242c197 |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4bcb1915081908834ced85d09e299 |
completed | March 1, 2026, 10:24 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ac667d2bdc8190b7d797683a4d3fe8 |
completed | March 7, 2026, 5:55 p.m. |
Created at: March 1, 2026, 7:45 p.m.