Triple
T19530989
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Belgian border near Hazeldonk |
E488650
|
entity |
| Predicate | nearbySettlement |
P350
|
FINISHED |
| Object | Hazeldonk |
—
|
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: Hazeldonk | Statement: [Belgian border near Hazeldonk, nearbySettlement, Hazeldonk]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hazeldonk Context triple: [Belgian border near Hazeldonk, nearbySettlement, Hazeldonk]
-
A.
Hazeldonk
chosen
Hazeldonk is a small locality in the southern Netherlands known primarily as a major motorway service and customs area near the Belgian border.
-
B.
Harksheide
Harksheide was a former municipality in Schleswig-Holstein, Germany, that later became part of the city of Norderstedt.
-
C.
Holleken
Holleken is a local railway station serving the suburban area near Brussels, Belgium.
-
D.
Hazendal
Hazendal is a residential suburb of Cape Town, South Africa, situated near Athlone on the Cape Flats.
-
E.
Haaltert
Haaltert is a municipality in the Belgian province of East Flanders, known for its rural character and location within the Denderstreek region.
- 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_69d8e8db5b6c8190984b61f91981f575 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6363ec6cc8190b9e9ac0196b288f9 |
completed | April 20, 2026, 2:20 p.m. |
Created at: April 10, 2026, 1:41 p.m.