Triple
T17855873
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Suffolk |
E445934
|
entity |
| Predicate | containsRiver |
P165
|
FINISHED |
| Object | River Lark |
—
|
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 Lark | Statement: [Suffolk, containsRiver, River Lark]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: River Lark Context triple: [Suffolk, containsRiver, River Lark]
-
A.
River Lark
chosen
The River Lark is a river in East Anglia, England, that flows through Suffolk and Cambridgeshire before joining the River Great Ouse.
-
B.
The Lark
The Lark is a stage play best known for featuring Julie Harris in a celebrated portrayal of Joan of Arc.
-
C.
The Lark
"The Lark" is a lyrical piano piece, often associated with Romantic-era Russian repertoire, known for its delicate, songlike melody and evocative, birdlike figurations.
-
D.
Lark Rise to Candleford
Lark Rise to Candleford is a British period drama television series, based on Flora Thompson’s semi-autobiographical novels, that portrays rural and small-town life in late 19th-century Oxfordshire.
-
E.
The Meadow
The Meadow is a large open green space within Delaware Park in Buffalo, New York, commonly used for recreation, events, and outdoor gatherings.
- 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_69d8b9f26f18819089c9e43250bee6ae |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e4978bd5e081909e192f6aada5235f |
completed | April 19, 2026, 8:51 a.m. |
Created at: April 10, 2026, 10:17 a.m.