Triple
T8393364
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1997 Red River flood |
E197994
|
entity |
| Predicate | naturalProcess |
P51498
|
FINISHED |
| Object | riverine flooding |
—
|
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: riverine flooding | Statement: [1997 Red River flood, naturalProcess, riverine flooding]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: naturalProcess Context triple: [1997 Red River flood, naturalProcess, riverine flooding]
-
A.
naturalOccurrence
Indicates that the related event or phenomenon happens in nature without direct human intervention or artificial cause.
-
B.
naturalForm
Indicates that one entity is the inherent, unaltered, or original form or state of another entity.
-
C.
naturalOrArtificial
Indicates that something is classified as either naturally occurring or artificially created.
-
D.
hasNature
Indicates that something possesses, exhibits, or is characterized by a particular inherent quality, essence, or fundamental type.
-
E.
originProcess
chosen
Indicates the process, activity, or mechanism from which an entity, condition, or outcome originally arises or is produced.
- 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_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. |
Created at: March 30, 2026, 6:03 p.m.