Triple
T20617283
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kolding railway station |
E506599
|
entity |
| Predicate | operator |
P179
|
FINISHED |
| Object | Arriva |
—
|
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: Arriva | Statement: [Kolding railway station, operator, Arriva]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Arriva Context triple: [Kolding railway station, operator, Arriva]
-
A.
Arriva
chosen
Arriva is a major European public transport company that operates bus, coach, train, tram, and waterbus services across multiple countries.
-
B.
Arriva Midlands
Arriva Midlands is a regional bus operator in the English Midlands, running local and interurban services across towns and cities such as Telford.
-
C.
Arriva North West
Arriva North West is a major regional bus operator providing public transport services across North West England.
-
D.
Govia
Govia is a major British train operating company formed as a joint venture between the Go-Ahead Group and Keolis, running several rail franchises in the United Kingdom.
-
E.
Arriva Rail North
Arriva Rail North was a British train operating company that ran regional and commuter rail services across Northern England under the Northern brand.
- 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_69e0b4bc90988190ac360aaf645efc1d |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6aadd30b88190af3a05527ad5ac64 |
completed | April 20, 2026, 10:38 p.m. |
Created at: April 16, 2026, 11:41 a.m.