Triple
T1328764
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Amsterdam City Swim |
E28392
|
entity |
| Predicate | usesBodyOfWater |
P8778
|
FINISHED |
| Object | Amsterdam canals |
—
|
LITERAL 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: Amsterdam canals | Statement: [Amsterdam City Swim, usesBodyOfWater, Amsterdam canals]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesBodyOfWater Context triple: [Amsterdam City Swim, usesBodyOfWater, Amsterdam canals]
-
A.
locatedInBodyOfWater
Indicates that an entity is situated within or on the surface of a specific body of water.
-
B.
connectedBodyOfWater
Indicates that two geographic locations are linked by a continuous body of water through which water can flow between them.
-
C.
hasWaterBodyOnWest
Indicates that a specified entity has a water body located to its west.
-
D.
appliesToWaterBody
chosen
Indicates that something (such as a rule, condition, property, or effect) is relevant or applicable specifically to a particular water body.
-
E.
adjacentToBodyOfWater
Indicates that one entity is directly next to or bordering a body of water, such as a lake, river, or ocean.
- F. None of above.
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_69a498540a2481909e807a762280d3ba |
completed | March 1, 2026, 7:49 p.m. |
| NER | Named-entity recognition | batch_69a4c1c30c948190afc6342b3dcda948 |
completed | March 1, 2026, 10:46 p.m. |
| PD | Predicate disambiguation | batch_69a4beef6a188190996f8775bdda8f6c |
completed | March 1, 2026, 10:34 p.m. |
Created at: March 1, 2026, 7:55 p.m.