Triple
T22565430
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Doldersum |
E557936
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Westerveld |
—
|
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: Westerveld | Statement: [Doldersum, locatedIn, Westerveld]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Westerveld Context triple: [Doldersum, locatedIn, Westerveld]
-
A.
Westerveld
chosen
Westerveld is a rural municipality in the Dutch province of Drenthe, known for its natural landscapes, historic villages, and prehistoric dolmens.
-
B.
Elstra
Elstra is a small town in the Bautzen district of the German federal state of Saxony.
-
C.
Voskuil
Voskuil is a Dutch surname most notably associated with the writer J.J. Voskuil, known for his extensive autobiographical novels.
-
D.
Tinbergen
Tinbergen is a Dutch surname most famously associated with brothers Jan and Niko Tinbergen, who were pioneering figures in economics and ethology respectively.
-
E.
Hondius
Hondius is a Dutch family name most famously associated with Jodocus Hondius, a prominent 16th–17th century cartographer and engraver known for his influential maps and atlases.
- 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_69e11e5ae4ac8190b1f503457603d969 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15fa9ebc8819098d74fb41e14bd7e |
completed | April 29, 2026, 1:32 a.m. |
Created at: April 16, 2026, 8:52 p.m.