Triple
T32334993
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sudbrook |
E826146
|
entity |
| Predicate | pumpingStationPurpose |
P40127
|
FINISHED |
| Object | drainage of Severn Tunnel |
—
|
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: drainage of Severn Tunnel | Statement: [Sudbrook, pumpingStationPurpose, drainage of Severn Tunnel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: pumpingStationPurpose Context triple: [Sudbrook, pumpingStationPurpose, drainage of Severn Tunnel]
-
A.
hasPumpingStation
Indicates that one entity possesses, contains, or is served by a pumping station associated with it.
-
B.
powerPlantPurpose
Indicates that a power plant exists or is used for a specified purpose or function.
-
C.
parkEstablishmentPurpose
Indicates the intended purpose or primary reason for which a park was established.
-
D.
purposeOfConstruction
chosen
Indicates that one entity was constructed or built in order to serve, enable, or fulfill the function, goal, or intended use represented by another entity.
-
E.
towerPurpose
Indicates the primary function or intended use that a tower is designed or employed to serve.
- 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_69f34913d9048190befaa634025232be |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6be1779cc8190abe386c03d31d385 |
completed | May 3, 2026, 3:16 a.m. |
| PD | Predicate disambiguation | batch_69f6b633e0c88190a727bb7d2751e2d5 |
completed | May 3, 2026, 2:43 a.m. |
Created at: May 1, 2026, 12:48 a.m.