Triple
T8393347
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1997 Red River flood |
E197994
|
entity |
| Predicate | floodStage |
P81975
|
FINISHED |
| Object | record crest at Grand Forks |
—
|
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: record crest at Grand Forks | Statement: [1997 Red River flood, floodStage, record crest at Grand Forks]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: floodStage Context triple: [1997 Red River flood, floodStage, record crest at Grand Forks]
-
A.
floodGauge
Indicates that a device or measurement point is used to monitor and record the level or intensity of flooding at a specific location.
-
B.
floodEvent
Indicates an occurrence of a flooding event affecting a location, time period, or set of impacted entities.
-
C.
hasFloodRisk
Indicates that an entity is exposed to a potential or expected risk of flooding under certain conditions.
-
D.
floodRecord
Indicates that an entity serves as a documented record or report of a flood event affecting another entity or area.
-
E.
floodCause
Indicates that one entity is the cause or source of a flood affecting another entity or area.
- F. None of above. chosen
Provenance (4 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_69ca82f816bc8190ab321c07d72208c1 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb8184788081909e9857afff629985 |
completed | March 31, 2026, 8:10 a.m. |
| PD | Predicate disambiguation | batch_69cb70d24b248190a326aa6804f942b5 |
completed | March 31, 2026, 6:59 a.m. |
| PDg | Predicate description generation | batch_69cb77690720819099de1e22b84a9563 |
completed | March 31, 2026, 7:27 a.m. |
Created at: March 30, 2026, 6:03 p.m.