Triple
T22112352
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lancaster district |
E546448
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | River Lune |
—
|
NE NERFINISHED |
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 Lune | Statement: [Lancaster district, contains, River Lune]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: River Lune Context triple: [Lancaster district, contains, River Lune]
-
A.
River Lune
chosen
The River Lune is a river in North West England that flows through Cumbria and Lancashire before emptying into the Irish Sea near Lancaster.
-
B.
River Leen
The River Leen is a small river in Nottinghamshire, England, that flows through the city of Nottingham before joining the River Trent.
-
C.
Derwent
Derwent is a renowned British brand of high-quality art pencils and drawing materials widely used by artists and illustrators.
-
D.
Derwent
Derwent is a character in Herman Melville’s epic poem "Clarel," serving as one of the intellectual and philosophical voices in the work’s exploration of faith and doubt.
-
E.
Derwent
Derwent is a well-known intellectual property and patent research brand offering tools and analytics for innovation and competitive intelligence.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e11e38b3848190ac3a4fa97d56e65a |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f1294ae7608190901745384a023bab |
completed | April 28, 2026, 9:40 p.m. |
Created at: April 16, 2026, 8:31 p.m.