Triple
T32493984
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Agulhas Return Current |
E830466
|
entity |
| Predicate | dynamicType |
P138320
|
FINISHED |
| Object | strong frontal current |
—
|
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: strong frontal current | Statement: [Agulhas Return Current, dynamicType, strong frontal current]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dynamicType Context triple: [Agulhas Return Current, dynamicType, strong frontal current]
-
A.
definitionType
Indicates the specific kind or category of definition that characterizes how one entity is defined in relation to another.
-
B.
deltaType
Indicates a classification of the kind or category of change (difference) that has occurred between two related states or versions.
-
C.
dynamicShape
Indicates that an entity’s shape changes over time or in response to certain conditions or interactions.
-
D.
descriptorType
chosen
Indicates that one entity serves as a descriptive attribute or classification of another entity.
-
E.
InType
Indicates that an entity belongs to, is categorized under, or is an instance of a specified type or class.
- 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_69f34920aa4081908d8fb0277414b911 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6c409752081909622d522bbac6557 |
completed | May 3, 2026, 3:42 a.m. |
| PD | Predicate disambiguation | batch_69f6bd25bed08190befcabd3a41ffadf |
completed | May 3, 2026, 3:12 a.m. |
Created at: May 1, 2026, 12:59 a.m.