Triple
T20859408
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tropical Storm Bret (2005) |
E513573
|
entity |
| Predicate | stormClassification |
P98399
|
FINISHED |
| Object | tropical storm in the Atlantic basin |
—
|
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: tropical storm in the Atlantic basin | Statement: [Tropical Storm Bret (2005), stormClassification, tropical storm in the Atlantic basin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: stormClassification Context triple: [Tropical Storm Bret (2005), stormClassification, tropical storm in the Atlantic basin]
-
A.
typicalStormType
Indicates the kind of storm that is most commonly or characteristically associated with a given context or location.
-
B.
SaffirSimpsonScaleCategory
Indicates the hurricane’s classification level on the Saffir–Simpson scale based on its sustained wind speed and associated potential damage.
-
C.
stormNameList
Indicates that a storm is included in a designated list of named storms.
-
D.
stormedBy
Indicates that an entity is subjected to a forceful or aggressive assault, attack, or rush by another entity.
-
E.
climateEventType
chosen
Indicates the specific kind or category of a climate-related event associated with an entity or occurrence.
- 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_69e0b4f5b01081909452f654d2fc3f50 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c3aabef4819098f0fd24dcc27dbd |
completed | April 21, 2026, 12:24 a.m. |
| PD | Predicate disambiguation | batch_69e5c9a593f481908beb457c29f1ce73 |
completed | April 20, 2026, 6:37 a.m. |
Created at: April 16, 2026, 12:44 p.m.