Triple
T3167128
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kalverstraat |
E66237
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Spui |
E25956
|
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: Spui | Statement: [Kalverstraat, near, Spui]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Spui Context triple: [Kalverstraat, near, Spui]
-
A.
Spui
chosen
Spui is a central square and tram hub in Amsterdam, Netherlands, known for its bookstores, cultural venues, and proximity to historic canals.
-
B.
Spui
Spui is a small tidal river in South Holland, Netherlands, that branches off from the Oude Maas and plays a role in the region’s delta water system.
-
C.
Bruinisse
Bruinisse is a fishing village and tourist destination in the Dutch province of Zeeland, known for its mussel industry and location on the Grevelingen.
-
D.
Peraia
Peraia is a locality in Greece known historically as the place where Ecuadorian statesman and first president Juan José Flores died.
-
E.
Sorpesee
Sorpesee is a popular artificial lake in the Sauerland region of Germany, known for recreation, water sports, and scenic surroundings.
- 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_69ad8585d7988190af37365331093ccd |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada643e3e481908f4526d66e36e150 |
completed | March 8, 2026, 4:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b235e108cc81909d5733bd00cb0bee |
completed | March 12, 2026, 3:41 a.m. |
Created at: March 8, 2026, 3:06 p.m.