Triple
T14252512
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zwolle |
E353304
|
entity |
| Predicate | locatedOnRiver |
P165
|
FINISHED |
| Object | Zwarte Water |
E495132
|
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: Zwarte Water | Statement: [Zwolle, locatedOnRiver, Zwarte Water]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Zwarte Water Context triple: [Zwolle, locatedOnRiver, Zwarte Water]
-
A.
Zwarte Water
chosen
Zwarte Water is a river in the Dutch province of Overijssel that flows through several towns before joining the IJssel near Zwolle.
-
B.
Achterwasser
Achterwasser is a coastal lagoon on the German island of Usedom, connected to the Baltic Sea and known for its shallow waters and scenic natural surroundings.
-
C.
Rotes Wasser
Rotes Wasser is a small river in Germany that serves as a tributary of the Ohm.
-
D.
Den Oever
Den Oever is a village in the Dutch province of North Holland, known as a fishing port and gateway to the Afsluitdijk on the former island of Wieringen.
-
E.
River Suck
River Suck is a major river in western Ireland that flows through counties such as Roscommon and Galway before joining the River Shannon.
- 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_69d8278c43e08190824146f4632b89a5 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de6297f38c819090d7c7fd8bfa2e9e |
completed | April 14, 2026, 3:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd325a14b881909522b6fbbcc6326f |
completed | May 8, 2026, 12:46 a.m. |
Created at: April 10, 2026, 1:08 a.m.