Triple
T24012481
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | DKG |
E594570
|
entity |
| Predicate | infrastructureOwnerContext |
P26836
|
FINISHED |
| Object | Network Rail |
—
|
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: Network Rail | Statement: [DKG, infrastructureOwnerContext, Network Rail]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: infrastructureOwnerContext Context triple: [DKG, infrastructureOwnerContext, Network Rail]
-
A.
hasInfrastructureOwner
chosen
Indicates that one entity owns or is responsible for the infrastructure associated with another entity.
-
B.
ownerOfInfrastructureUsed
Indicates that one entity owns the infrastructure that is being used by another entity or activity.
-
C.
hasInfrastructureOwnerType
Indicates the type or category of entity that owns or is responsible for a given piece of infrastructure.
-
D.
predecessorInfrastructureOwner
Indicates that one infrastructure owner previously held ownership or responsibility before another in a temporal succession.
-
E.
ownedInfrastructureClass
Indicates that an entity possesses or controls infrastructure belonging to a specified class or category.
- 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_69e288bc8f608190ac4af29f0bd1c744 |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1d59ee0a08190ad1e1bc2dad1dda7 |
completed | April 29, 2026, 9:55 a.m. |
| PD | Predicate disambiguation | batch_69f17639d23c8190bed93434e2f9230a |
completed | April 29, 2026, 3:08 a.m. |
Created at: April 17, 2026, 9:41 p.m.