Triple
T2638420
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Great Australian Bight |
E62802
|
entity |
| Predicate | waveExposure |
P20654
|
FINISHED |
| Object | highly exposed to Southern Ocean storms |
—
|
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: highly exposed to Southern Ocean storms | Statement: [Great Australian Bight, waveExposure, highly exposed to Southern Ocean storms]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: waveExposure Context triple: [Great Australian Bight, waveExposure, highly exposed to Southern Ocean storms]
-
A.
waveType
Indicates the specific kind or category of wave associated with an entity or interaction (e.g., type of signal, motion, or oscillation).
-
B.
pressureWaveCircledEarthTimes
Indicates how many times a pressure wave propagated around the entire Earth.
-
C.
exposureType
Indicates the specific manner or context in which one entity is exposed to another entity, condition, or influence.
-
D.
hasWaveClimate
chosen
Indicates a relationship where a location or coastal area is characterized by a particular pattern or regime of wave conditions (such as height, period, and direction).
-
E.
exposes
Indicates making something visible, known, or vulnerable by removing cover, concealment, or protection.
- 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_69ab4c3f2dcc819082df80f5e032f690 |
completed | March 6, 2026, 9:50 p.m. |
| NER | Named-entity recognition | batch_69abd8e470ac8190bd0d6de6805afcd0 |
completed | March 7, 2026, 7:51 a.m. |
| PD | Predicate disambiguation | batch_69abd812849881908f956845a80e0205 |
completed | March 7, 2026, 7:47 a.m. |
Created at: March 6, 2026, 9:53 p.m.