Triple
T17713457
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Utrechtse Heuvelrug |
E441626
|
entity |
| Predicate | borderedBy |
P224
|
FINISHED |
| Object | Bunnik |
—
|
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: Bunnik | Statement: [Utrechtse Heuvelrug, borderedBy, Bunnik]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bunnik Context triple: [Utrechtse Heuvelrug, borderedBy, Bunnik]
-
A.
Bunnik
chosen
Bunnik is a small Dutch municipality and village in the central Netherlands, known for its historic sites and green surroundings near the city of Utrecht.
-
B.
Kortenhoef
Kortenhoef is a village in the Dutch province of North Holland, known for its lakes, peatlands, and scenic natural surroundings.
-
C.
Nuenen
Nuenen is a village in the southern Netherlands, known for its association with both the painter Vincent van Gogh and computer scientist Edsger W. Dijkstra.
-
D.
Kloosterburen
Kloosterburen is a small village in the Dutch province of Groningen, known for its historic churches and rural character.
-
E.
Bloemendaal
Bloemendaal is a coastal municipality in North Holland, Netherlands, known for its beaches, dunes, and affluent residential areas.
- 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_69d8b9ea20b48190ace88bb46b01e6a9 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e4729cebd08190872be96a26d0f7ce |
completed | April 19, 2026, 6:13 a.m. |
Created at: April 10, 2026, 10:06 a.m.