Triple
T3137569
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rokin |
E65569
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Kalverstraat |
E66237
|
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: Kalverstraat | Statement: [Rokin, near, Kalverstraat]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kalverstraat Context triple: [Rokin, near, Kalverstraat]
-
A.
Kalverstraat
chosen
Kalverstraat is one of Amsterdam’s busiest and most famous shopping streets, known for its dense concentration of retail stores and central location.
-
B.
Servetstraat
Servetstraat is a small historic street located near Dom Square in the center of Utrecht, Netherlands.
-
C.
Paleisstraat
Paleisstraat is a central street in Amsterdam that runs alongside the Royal Palace and links Dam Square with the Jordaan area.
-
D.
Utrechtsestraat
Utrechtsestraat is a well-known shopping and dining street in central Amsterdam, noted for its historic canalside setting and mix of boutiques, cafés, and restaurants.
-
E.
Vijzelstraat
Vijzelstraat is a major street in central Amsterdam, Netherlands, running between the city’s historic canals and serving as an important traffic and commercial route.
- 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_69ad8581c25c8190b0d85ba9b9baa531 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada574509c81908a88bb10ea35516d |
completed | March 8, 2026, 4:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b354528b00819095fa9b8f28f2135c |
completed | March 13, 2026, 12:03 a.m. |
Created at: March 8, 2026, 3:05 p.m.