Triple
T23499975
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Duivendrecht |
E571812
|
entity |
| Predicate | railwayLinesPassThrough |
P848
|
FINISHED |
| Object | Amsterdam–Arnhem railway |
E29033
|
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: Amsterdam–Arnhem railway | Statement: [Duivendrecht, railwayLinesPassThrough, Amsterdam–Arnhem railway]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: railwayLinesPassThrough Context triple: [Duivendrecht, railwayLinesPassThrough, Amsterdam–Arnhem railway]
-
A.
railwayLine
chosen
Indicates that there is a railway line connection or route associated with or passing through the referenced entity.
-
B.
railwayLineNow
Indicates that a previously existing railway line has been replaced, succeeded, or is currently represented by a new or different railway line.
-
C.
railwayConnectsTo
Indicates that one railway line, track, or network is directly linked or joined to another, allowing trains to move between them.
-
D.
railInfrastructureServed
Indicates that a rail infrastructure facility or segment is served, accessed, or operated by a particular service, operator, or network.
-
E.
railwayLineUsage
Indicates how a railway line is used, such as the type or purpose of traffic or operations it supports.
- F. None of above.
Provenance (4 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_69e245b4829881909b77a70e942bbd54 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1a8fb71c08190a30500b3f63a9ce6 |
completed | April 29, 2026, 6:45 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0f75ed2b288190a0308290784ae994 |
completed | May 21, 2026, 9:15 p.m. |
| PD | Predicate disambiguation | batch_69f0621165c08190a0b27b1319733959 |
completed | April 28, 2026, 7:30 a.m. |
Created at: April 17, 2026, 6:06 p.m.