Triple
T15735278
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | River Frome (Dorset) |
E381451
|
entity |
| Predicate | crossedBy |
P416
|
FINISHED |
| Object | A35 road |
—
|
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: A35 road | Statement: [River Frome (Dorset), crossedBy, A35 road]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: A35 road Context triple: [River Frome (Dorset), crossedBy, A35 road]
-
A.
A35 road
chosen
The A35 road is a major trunk route in southern England that runs through Dorset and neighboring counties, linking towns such as Dorchester with the wider regional road network.
-
B.
A305 road
The A305 road is a local A-class route in southwest London connecting areas such as Richmond and Twickenham and forming part of the urban road network across the River Thames.
-
C.
A30 road
The A30 road is a major trunk route in southern England that runs from London through counties including Surrey toward the southwest.
-
D.
A33 road
The A33 road is a major route in southern England connecting Reading and Basingstoke to Winchester and the M3 motorway.
-
E.
A34 road
The A34 road is a regional route in Northern Ireland that connects towns such as Lisnaskea, serving as an important local transport link.
- 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_69d86d9cdb648190bf3171be0bd7d872 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e04fd586a88190aa1b1b88368d386f |
completed | April 16, 2026, 2:56 a.m. |
Created at: April 10, 2026, 4:46 a.m.