Triple
T24502292
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2014 Southeast Europe floods |
E617965
|
entity |
| Predicate | highestRecordedWaterLevelLocation |
P72076
|
FINISHED |
| Object | Sava River at Šabac |
—
|
NE NERFINISHED |
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: Sava River at Šabac | Statement: [2014 Southeast Europe floods, highestRecordedWaterLevelLocation, Sava River at Šabac]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: highestRecordedWaterLevelLocation Context triple: [2014 Southeast Europe floods, highestRecordedWaterLevelLocation, Sava River at Šabac]
-
A.
waterLevelHighestIn
Indicates that the referenced location or container has the greatest water level compared to a specified set of locations or containers.
-
B.
floodPeakLocation
chosen
Indicates the location at which the maximum intensity or highest level of a flood event occurs.
-
C.
reservoirElevation
Indicates the height or level of water stored in a reservoir relative to a defined reference point.
-
D.
waterLevelRise
Indicates that the level of water in a given area or container has increased over time.
-
E.
riverMouthElevation
Indicates the elevation at which a river reaches its mouth or endpoint, typically where it flows into another body of water.
- 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_69e2d7f682108190a1a7ca5fd485ee8a |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f2a9d912e88190bc39c05a9d7f407e |
completed | April 30, 2026, 1:01 a.m. |
| PD | Predicate disambiguation | batch_69f2a6a4580481908fddc385f5262f95 |
completed | April 30, 2026, 12:47 a.m. |
Created at: April 18, 2026, 2:23 a.m.