Triple
T15501747
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stelling van Amsterdam |
E378973
|
entity |
| Predicate | locatedNear |
P294
|
FINISHED |
| Object | IJmeer |
E33325
|
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: IJmeer | Statement: [Stelling van Amsterdam, locatedNear, IJmeer]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: IJmeer Context triple: [Stelling van Amsterdam, locatedNear, IJmeer]
-
A.
IJmeer
chosen
IJmeer is a shallow lake in the Netherlands, located east of Amsterdam and forming part of the IJsselmeer lake system.
-
B.
Bijlmermeer
Bijlmermeer is a residential neighborhood in Amsterdam, Netherlands, known for its large-scale modernist high-rise housing and diverse, multicultural population.
-
C.
Zaan region
The Zaan region is an industrial and historical area in North Holland, Netherlands, known for its traditional windmills, early industrial heritage, and picturesque riverside towns such as Zaandam.
-
D.
Strandvliet
Strandvliet is a metro station in Amsterdam that serves passengers on the city's rapid transit network.
-
E.
Drecht
Drecht is a lesser-known Dutch river whose waters help form the Amstel through their confluence.
- 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_69d85cd53a7c819080f5b9042c4c199e |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e03fcc5bb88190b8a9a81419a9a38b |
completed | April 16, 2026, 1:47 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff4c345f888190be7a684f3bd86324 |
completed | May 9, 2026, 3:01 p.m. |
Created at: April 10, 2026, 3:54 a.m.