Triple
T14185698
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rotterdam Metro |
E351568
|
entity |
| Predicate | terminus |
P388
|
FINISHED |
| Object | De Terp |
E682610
|
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: De Terp | Statement: [Rotterdam Metro, terminus, De Terp]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: De Terp Context triple: [Rotterdam Metro, terminus, De Terp]
-
A.
De Terp
chosen
De Terp is a metro station in the Dutch city of Capelle aan den IJssel that serves as a local stop on the Rotterdam metro network.
-
B.
Begijnhof
Begijnhof is a historic, secluded courtyard in central Amsterdam known for its preserved medieval houses and former beguine community.
-
C.
Malieveld
Malieveld is a large open field and event grounds in The Hague, Netherlands, known for hosting demonstrations, festivals, and public gatherings.
-
D.
Voorhout
Voorhout is a village in South Holland, Netherlands, that forms part of the municipality of Teylingen.
-
E.
Muiderberg
Muiderberg is a small Dutch village in North Holland, known for its location on the shores of the IJmeer and its historic Jewish cemetery.
- 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_69d8278834a08190b0f1784e58d7b99c |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de61cd5778819092a03597bcdcc182 |
completed | April 14, 2026, 3:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd280656a881909c565b99e85ae9bd |
completed | May 8, 2026, 12:02 a.m. |
Created at: April 10, 2026, 1:03 a.m.