Triple
T18793902
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Spaarne River |
E459582
|
entity |
| Predicate | hasBridge |
P386
|
FINISHED |
| Object | Schoterbrug |
—
|
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: Schoterbrug | Statement: [Spaarne River, hasBridge, Schoterbrug]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Schoterbrug Context triple: [Spaarne River, hasBridge, Schoterbrug]
-
A.
Schoterbrug
chosen
Schoterbrug is a bridge spanning the Spaarne River in Haarlem, Netherlands, serving as an important local traffic connection.
-
B.
Cellebroederspoort
Cellebroederspoort is a historic city gate in Kampen, the Netherlands, known for its Renaissance architecture and role as part of the town’s former fortifications.
-
C.
Berkelpoort
Berkelpoort is a historic medieval city gate in Zutphen, the Netherlands, that once formed part of the town’s defensive fortifications along the Berkel river.
-
D.
Rozengracht
Rozengracht is a prominent street in Amsterdam’s Jordaan neighborhood, known for its historic canalside buildings, shops, and cafés.
-
E.
Blokhuispoort
Blokhuispoort is a former prison complex in Leeuwarden, Netherlands, that has been transformed into a cultural and creative hub with museums, studios, and public spaces.
- 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_69d8d396f54c8190ba49db31e8743842 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e5a01cc0c0819098ef4326e82ff524 |
completed | April 20, 2026, 3:40 a.m. |
Created at: April 10, 2026, 11:53 a.m.