Triple
T21538795
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Second Severn Crossing |
E531420
|
entity |
| Predicate | hasTollPlazasFormerlyOn |
P24137
|
FINISHED |
| Object | westbound carriageway |
—
|
LITERAL FINISHED |
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: westbound carriageway | Statement: [Second Severn Crossing, hasTollPlazasFormerlyOn, westbound carriageway]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTollPlazasFormerlyOn Context triple: [Second Severn Crossing, hasTollPlazasFormerlyOn, westbound carriageway]
-
A.
hasTollPlazaRemoved
chosen
Indicates that a previously existing toll plaza associated with an entity has been removed or decommissioned.
-
B.
formerTollRoad
Indicates that a road previously operated as a toll road but is no longer tolled.
-
C.
hasTollBoothsAt
Indicates that toll booths are present at or associated with a particular location or segment of infrastructure.
-
D.
previouslyHadToll
Indicates that a location, route, or facility once required a toll for use but no longer does.
-
E.
isTollFacilityOf
Indicates that a facility (such as a toll booth, plaza, or gantry) is part of, or used to collect tolls for, a specific toll road or toll transportation infrastructure.
- F. None of above.
Provenance (3 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_69e0c45e5b8881908ac18fc2f493b114 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ee9d10a2888190bc4e502a829c76a4 |
completed | April 26, 2026, 11:17 p.m. |
| PD | Predicate disambiguation | batch_69e6320766308190ba5dca2f7c826aa4 |
completed | April 20, 2026, 2:02 p.m. |
Created at: April 16, 2026, 6:27 p.m.