Triple
T24115912
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oberkassel |
E597510
|
entity |
| Predicate | hasRiversidePromenade |
P12289
|
FINISHED |
| Object | Rhine riverside promenade in Oberkassel |
—
|
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: Rhine riverside promenade in Oberkassel | Statement: [Oberkassel, hasRiversidePromenade, Rhine riverside promenade in Oberkassel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRiversidePromenade Context triple: [Oberkassel, hasRiversidePromenade, Rhine riverside promenade in Oberkassel]
-
A.
hasPromenade
chosen
Indicates that one entity features or includes a promenade, typically as a designated walkway or leisure area associated with it.
-
B.
hasRiverBeach
Indicates that a location includes or is characterized by a beach area along a river.
-
C.
hasRiverfrontDistrict
Indicates that a place includes a designated district or area that directly borders and is oriented around a river.
-
D.
hasWaterfrontPark
Indicates that a place or area includes or is associated with a park located directly along a body of water.
-
E.
isRiverside
Indicates that one entity is located beside or along the bank of a river in relation to another entity.
- 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_69e288c74200819098ab875b592cb39f |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1dedebb748190b8fe295d6dc0a9a7 |
completed | April 29, 2026, 10:35 a.m. |
| PD | Predicate disambiguation | batch_69f17651458c8190bbfd301883e46085 |
completed | April 29, 2026, 3:09 a.m. |
Created at: April 17, 2026, 11:04 p.m.