Triple
T479426
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | southern right whale |
E9133
|
entity |
| Predicate | surfaceBehavior |
P14798
|
FINISHED |
| Object | frequent breaching |
—
|
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: frequent breaching | Statement: [southern right whale, surfaceBehavior, frequent breaching]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: surfaceBehavior Context triple: [southern right whale, surfaceBehavior, frequent breaching]
-
A.
surfaceType
Indicates the kind or classification of surface associated with an entity or interaction.
-
B.
surfaceAccess
Indicates that one entity provides a means for another entity to reach, enter, or interact with a surface or outer layer.
-
C.
texture
Indicates the surface quality or feel of an entity as perceived by touch or appearance, such as being smooth, rough, soft, or coarse.
-
D.
surfaceFreezesPartiallyIn
Indicates that a surface undergoes a freezing process in which only part of it becomes frozen within a given medium, environment, or container.
-
E.
behaviorNear
Indicates that one entity exhibits a behavior or action in close spatial proximity to another entity.
- 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_69a2e7ff81708190b0507a24a997232c |
completed | Feb. 28, 2026, 1:05 p.m. |
| NER | Named-entity recognition | batch_69a2f056459881909749764cc4a7f9e8 |
completed | Feb. 28, 2026, 1:40 p.m. |
| PD | Predicate disambiguation | batch_69a2edf1d5848190a7da27e2fddc136f |
completed | Feb. 28, 2026, 1:30 p.m. |
| PDg | Predicate description generation | batch_69a2ef4030608190b39852b347a505ca |
completed | Feb. 28, 2026, 1:36 p.m. |
Created at: Feb. 28, 2026, 1:12 p.m.