Triple
T29175007
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2011 Souris River flood |
E739581
|
entity |
| Predicate | riverCrestedAboveFloodStage |
P81975
|
FINISHED |
| Object | Minot, North Dakota |
—
|
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: Minot, North Dakota | Statement: [2011 Souris River flood, riverCrestedAboveFloodStage, Minot, North Dakota]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: riverCrestedAboveFloodStage Context triple: [2011 Souris River flood, riverCrestedAboveFloodStage, Minot, North Dakota]
-
A.
floodStage
chosen
Indicates that a water body’s level has reached or exceeded the defined height at which flooding is expected to begin or become hazardous.
-
B.
floodGauge
Indicates that a device or measurement point is used to monitor and record the level or intensity of flooding at a specific location.
-
C.
riverStatusAtLocation
Indicates the condition or state of a river at a specific geographic location.
-
D.
waterLevelHigherThan
Indicates that the water level of one entity is greater than the water level of another entity.
-
E.
raisesWaterway
Indicates that one entity elevates or increases the level, height, or flow of a waterway relative to another entity or state.
- 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_69f07cb6394c8190ab7842c48e699e2a |
completed | April 28, 2026, 9:24 a.m. |
| NER | Named-entity recognition | batch_69f6afebd7ec8190ab696f363d84abf0 |
completed | May 3, 2026, 2:16 a.m. |
| PD | Predicate disambiguation | batch_69f6aca204148190850a3dc325bc07b7 |
completed | May 3, 2026, 2:02 a.m. |
Created at: April 28, 2026, 11:54 a.m.