Triple
T5813030
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maashees |
E128915
|
entity |
| Predicate | hasNearbySettlement |
P4647
|
FINISHED |
| Object | Boxmeer |
E156359
|
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: Boxmeer | Statement: [Maashees, hasNearbySettlement, Boxmeer]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Boxmeer Context triple: [Maashees, hasNearbySettlement, Boxmeer]
-
A.
Boxmeer
chosen
Boxmeer is a town in the Dutch province of North Brabant, known historically as a former municipality and now part of the Land van Cuijk region.
-
B.
Eemhaven
Eemhaven is a major container and short-sea shipping terminal area within the Port of Rotterdam in the Netherlands.
-
C.
Hulst
Hulst is a historic fortified town and municipality in the Dutch province of Zeeland, near the border with Belgium.
-
D.
Aalten
Aalten is a municipality and town in the province of Gelderland in the eastern Netherlands, near the German border.
-
E.
Hoeksche Waard
Hoeksche Waard is a rural island and municipality in South Holland, Netherlands, known for its agricultural landscape and small towns.
- 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_69c0084788848190bcf71f6bc5d71597 |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c02b56044c8190847478a342d441c2 |
completed | March 22, 2026, 5:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c80294e8bc8190bfaab1d02e1640a6 |
completed | March 28, 2026, 4:32 p.m. |
Created at: March 22, 2026, 3:52 p.m.