Triple
T20163129
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Noord/Zuidlijn |
E491763
|
entity |
| Predicate | hasStation |
P35
|
FINISHED |
| Object | Noord |
—
|
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: Noord | Statement: [Noord/Zuidlijn, hasStation, Noord]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Noord Context triple: [Noord/Zuidlijn, hasStation, Noord]
-
A.
Noord
Noord is a major river in the western Netherlands that forms part of the Rhine–Meuse–Scheldt delta and serves as an important waterway for regional shipping and transport.
-
B.
Noord
Noord is a residential neighborhood located in the Dutch city of Tilburg.
-
C.
Noord
chosen
Noord is the northern terminus station of Amsterdam’s North–South metro line (Line 52), serving as a key public transport hub for the city’s northern districts.
-
D.
Zuid
Zuid is a major Amsterdam railway and metro station that serves as a key transport hub in the city’s southern business district.
-
E.
Nienoord
Nienoord is a historic Dutch estate and former noble manor known for its stately house, gardens, and heritage attractions in the province of Groningen.
- 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_69da6266c6888190bc1a3ecf24814d34 |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e66841b7d88190af3606f762d87b24 |
completed | April 20, 2026, 5:54 p.m. |
Created at: April 11, 2026, 11:35 p.m.