Triple
T24297365
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cardiff Central–Portsmouth Harbour |
E605999
|
entity |
| Predicate | operatesOnRailNetwork |
P15040
|
FINISHED |
| Object | National 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: National Rail | Statement: [Cardiff Central–Portsmouth Harbour, operatesOnRailNetwork, National Rail]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: operatesOnRailNetwork Context triple: [Cardiff Central–Portsmouth Harbour, operatesOnRailNetwork, National Rail]
-
A.
operatesRailNetworkOf
Indicates that one entity manages and runs the rail network belonging to or associated with another entity.
-
B.
appliesToRailwayNetwork
Indicates that something is relevant or specifically applicable to a railway network as a whole.
-
C.
belongsToRailNetwork
Indicates that something is part of, or included within, a specific rail network.
-
D.
usesRailInfrastructureOf
chosen
Indicates that one entity operates on, accesses, or otherwise makes use of the rail infrastructure owned or managed by another entity.
-
E.
connectsToRailwayNetwork
Indicates that one entity is physically or functionally linked to a railway network, allowing access or transfer between them.
- 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_69e29549335881909cbf27adcaba1cf0 |
completed | April 17, 2026, 8:17 p.m. |
| NER | Named-entity recognition | batch_69f2915ada688190aa9c4bdaa2f1617f |
completed | April 29, 2026, 11:16 p.m. |
| PD | Predicate disambiguation | batch_69f1c45c6ec081908401b69424428100 |
completed | April 29, 2026, 8:42 a.m. |
Created at: April 18, 2026, 12:09 a.m.