Triple
T20992390
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Western Fells |
E517055
|
entity |
| Predicate | hasAccessPoint |
P1985
|
FINISHED |
| Object | Lorton |
—
|
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: Lorton | Statement: [Western Fells, hasAccessPoint, Lorton]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lorton Context triple: [Western Fells, hasAccessPoint, Lorton]
-
A.
Lorton
Lorton is a suburban community in Fairfax County, Northern Virginia, known for its residential neighborhoods, proximity to major transportation routes, and redevelopment of the former Lorton Reformatory site.
-
B.
Lorton
chosen
Lorton is a small village and civil parish in Cumbria, England, situated in the scenic Lake District near the town of Cockermouth.
-
C.
Purcellville
Purcellville is a small town in western Loudoun County, Virginia, known for its historic downtown, rural character, and role as a gateway to the Blue Ridge and Virginia wine country.
-
D.
Leesburg
Leesburg is a historic town in Loudoun County that serves as a suburban hub of Northern Virginia near Washington, D.C.
-
E.
Leesburg
Leesburg is a small city in central Florida known for its historic downtown, numerous lakes, and annual festivals such as Bikefest.
- 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_69e0b5006e2881909fc2383f841740cc |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e6fc1cbb10819089e4f1445b921946 |
completed | April 21, 2026, 4:25 a.m. |
Created at: April 16, 2026, 1:50 p.m.