Triple
T24960248
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Palilula (Belgrade) |
E624585
|
entity |
| Predicate | spansBankOfRiver |
P39043
|
FINISHED |
| Object | left bank of the Danube |
—
|
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: left bank of the Danube | Statement: [Palilula (Belgrade), spansBankOfRiver, left bank of the Danube]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: spansBankOfRiver Context triple: [Palilula (Belgrade), spansBankOfRiver, left bank of the Danube]
-
A.
crossedByRiver
Indicates that a river passes across or through a specified area, feature, or route.
-
B.
betweenRiver
Indicates a spatial relationship where something is located in the area separating two rivers or lies in the intermediate region defined by them.
-
C.
locatedOnBankOfRiver
chosen
Indicates that one entity is situated along or directly adjacent to the bank of a specified river.
-
D.
riverBankOnOneSide
Indicates that a river flows adjacent to and borders only one side of a specified bank or land area.
-
E.
bordersAcrossRiver
Indicates that two regions or entities share a boundary with each other that is separated or defined by a river.
- 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_69e2ff23a3a88190b1b9743fe5e15f94 |
completed | April 18, 2026, 3:48 a.m. |
| NER | Named-entity recognition | batch_69f4242c447c8190bf7972390ac93814 |
completed | May 1, 2026, 3:55 a.m. |
| PD | Predicate disambiguation | batch_69f4210130d08190ae30b7943f7a0bbc |
completed | May 1, 2026, 3:41 a.m. |
Created at: April 18, 2026, 5:58 a.m.