Triple
T22170412
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Elephant and Castle roundabout |
E547905
|
entity |
| Predicate | connectsTo |
P845
|
FINISHED |
| Object | London 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: London Road | Statement: [Elephant and Castle roundabout, connectsTo, London Road]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: London Road Context triple: [Elephant and Castle roundabout, connectsTo, London Road]
-
A.
London Road
London Road was the historic name of Manchester Piccadilly railway station, one of the main rail hubs in Manchester, England.
-
B.
London Road
London Road is a major thoroughfare in Edinburgh, Scotland, forming part of the main eastern approach to the city centre.
-
C.
London Road
chosen
London Road is a street in the Elephant and Castle area of south London, forming part of a major thoroughfare connecting central London with the surrounding districts.
-
D.
London Road
London Road is a major thoroughfare in Glasgow, Scotland, running through the Parkhead area and serving as a key route in the city's east end.
-
E.
London Road
London Road is a major thoroughfare in Southend-on-Sea, England, known for its mix of shops, entertainment venues, and local businesses.
- 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_69e11e3c4c5c81908d336165816b12e0 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f12a67f4dc81909cc5f8d2c1fe6129 |
completed | April 28, 2026, 9:45 p.m. |
Created at: April 16, 2026, 8:34 p.m.