Triple
T7765138
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | KNSM Island |
E176124
|
entity |
| Predicate | hasStreet |
P959
|
FINISHED |
| Object |
KNSM-laan
KNSM-laan is a main residential and thoroughfare street on Amsterdam’s KNSM Island, known for its modern architecture and waterfront urban design.
|
E687125
|
NE FINISHED |
How this triple was built (4 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: KNSM-laan | Statement: [KNSM Island, hasStreet, KNSM-laan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: KNSM-laan Context triple: [KNSM Island, hasStreet, KNSM-laan]
-
A.
Heemraadlaan
Heemraadlaan is a metro station in Spijkenisse, Netherlands, serving as part of the Rotterdam Metro network.
-
B.
Koekamp
Koekamp is a historic green park and deer reserve on the edge of central The Hague in the Netherlands.
-
C.
Langerak
Langerak is a small village in the Dutch province of South Holland, known for its rural character and location along the Lek River.
-
D.
Raalte
Raalte is a town and municipality in the Dutch province of Overijssel, known for its agricultural surroundings and regional festivals.
-
E.
Klaaswaal
Klaaswaal is a village in the Dutch province of South Holland, known for its rural character and location on the island of Hoeksche Waard.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: KNSM-laan Triple: [KNSM Island, hasStreet, KNSM-laan]
Generated description
KNSM-laan is a main residential and thoroughfare street on Amsterdam’s KNSM Island, known for its modern architecture and waterfront urban design.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: KNSM-laan Target entity description: KNSM-laan is a main residential and thoroughfare street on Amsterdam’s KNSM Island, known for its modern architecture and waterfront urban design.
-
A.
Heemraadlaan
Heemraadlaan is a metro station in Spijkenisse, Netherlands, serving as part of the Rotterdam Metro network.
-
B.
Koekamp
Koekamp is a historic green park and deer reserve on the edge of central The Hague in the Netherlands.
-
C.
Langerak
Langerak is a small village in the Dutch province of South Holland, known for its rural character and location along the Lek River.
-
D.
Raalte
Raalte is a town and municipality in the Dutch province of Overijssel, known for its agricultural surroundings and regional festivals.
-
E.
Klaaswaal
Klaaswaal is a village in the Dutch province of South Holland, known for its rural character and location on the island of Hoeksche Waard.
- F. None of above. chosen
Provenance (5 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_69c69962923c8190ac74d28b4f9fe0a0 |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c7043279748190b30882e9cc6cca54 |
completed | March 27, 2026, 10:26 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c8c7de604c81908f503e1553795d38 |
completed | March 29, 2026, 6:34 a.m. |
| NEDg | Description generation | batch_69c8c8b75b848190a67de2040d563f86 |
completed | March 29, 2026, 6:37 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c8c941814081909d299df5cd714c71 |
completed | March 29, 2026, 6:40 a.m. |
Created at: March 27, 2026, 4:09 p.m.