Triple
T23309017
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Korps Mariniers |
E590529
|
entity |
| Predicate | garrison |
P75
|
FINISHED |
| Object | Texel |
—
|
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: Texel | Statement: [Korps Mariniers, garrison, Texel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Texel Context triple: [Korps Mariniers, garrison, Texel]
-
A.
Texel
chosen
Texel is the largest and most populated of the West Frisian Islands off the northwestern coast of the Netherlands, known for its beaches, dunes, and nature reserves.
-
B.
Vlieland
Vlieland is a sparsely populated Dutch Wadden Sea island known for its wide beaches, dunes, and car-free, nature-focused tourism.
-
C.
Ameland
Ameland is a Dutch Wadden Sea island known for its sandy beaches, dunes, and nature reserves, popular as a holiday destination in the northern Netherlands.
-
D.
Kennemerland
Kennemerland is a coastal historical region in the northwest of the Netherlands, known for its dunes, beaches, and old trading towns.
-
E.
Opsterland
Opsterland is a municipality in the province of Friesland in the northern Netherlands, known for its rural landscape and small villages.
- 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_69e25d1d32188190948eb76909d1dcc3 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f19729f7a4819092a1d24415b3df7a |
completed | April 29, 2026, 5:29 a.m. |
Created at: April 17, 2026, 5:05 p.m.