Triple
T21785138
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kortessem |
E537815
|
entity |
| Predicate | locatedNear |
P294
|
FINISHED |
| Object | Tongeren |
—
|
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: Tongeren | Statement: [Kortessem, locatedNear, Tongeren]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tongeren Context triple: [Kortessem, locatedNear, Tongeren]
-
A.
Tongeren
chosen
Tongeren is a historic city in eastern Belgium, known as the country’s oldest town and for its well-preserved Roman and medieval heritage.
-
B.
Ternaard
Ternaard is a small village in the Dutch province of Friesland, known for its rural character and location near the Wadden Sea.
-
C.
Yerseke
Yerseke is a Dutch village in the province of Zeeland, best known for its mussel and oyster farming along the Eastern Scheldt.
-
D.
Betuwe
Betuwe is a fertile riverine region in the Dutch province of Gelderland, renowned for its extensive fruit orchards and scenic landscapes between the Rhine and Waal rivers.
-
E.
Groesbeek
Groesbeek is a village in the Dutch province of Gelderland, known for its hilly landscape, World War II history, and wine production.
- 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_69e0c47198f881908cb0d237266c10e9 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f04630f4f08190910b9e499a4249ca |
completed | April 28, 2026, 5:31 a.m. |
Created at: April 16, 2026, 6:52 p.m.