Triple
T3512886
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ProRail |
E74236
|
entity |
| Predicate | collaboratesWith |
P37
|
FINISHED |
| Object | Arriva Nederland |
E119079
|
NE 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: Arriva Nederland | Statement: [ProRail, collaboratesWith, Arriva Nederland]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Arriva Nederland Context triple: [ProRail, collaboratesWith, Arriva Nederland]
-
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 UK Trains
Arriva UK Trains is a major British train operating company that manages several passenger rail franchises and services across the United Kingdom.
-
C.
Arriva Trains Northern
Arriva Trains Northern was a former British train operating company that provided regional and commuter rail services across Northern England.
-
D.
Abellio
Abellio is a Dutch-based public transport company that operates train and bus services in the United Kingdom and parts of Europe.
-
E.
Keolis
Keolis is a major French public transport operator that manages and operates bus, tram, metro, and rail networks in numerous cities worldwide.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ad85cfb5c881909c9a2edd9d6043cc |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adbc2d0bf481909d1f19a87d147b63 |
completed | March 8, 2026, 6:13 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b37e76c3a08190831402ff0c680196 |
completed | March 13, 2026, 3:03 a.m. |
Created at: March 8, 2026, 3:19 p.m.