Triple
T26091643
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Middleton, South Australia |
E658138
|
entity |
| Predicate | surfQuality |
P142836
|
FINISHED |
| Object | consistent beach breaks |
—
|
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: consistent beach breaks | Statement: [Middleton, South Australia, surfQuality, consistent beach breaks]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: surfQuality Context triple: [Middleton, South Australia, surfQuality, consistent beach breaks]
-
A.
hasSurfQuality
chosen
Indicates that something possesses a particular level or characteristic of surf quality, such as wave suitability or conditions for surfing.
-
B.
surfaceQuality
Indicates the condition or characteristics of an entity’s outer surface, such as its smoothness, roughness, or finish.
-
C.
hasSurfaceQuality
Indicates that one entity possesses a particular characteristic or condition of its surface.
-
D.
surfReliability
Indicates how consistently and dependably a surf-related condition, service, or performance meets expected standards over time.
-
E.
surfSpotType
Indicates the type or category of a surf spot based on its wave or break characteristics.
- 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_69ee5bbfc4d08190a1b206d0ac3a1e8d |
completed | April 26, 2026, 6:38 p.m. |
| NER | Named-entity recognition | batch_69f607329ac88190b415a64e2fdc2ac2 |
completed | May 2, 2026, 2:16 p.m. |
| PD | Predicate disambiguation | batch_69f5b0021da88190bdd4cf2698c23edf |
completed | May 2, 2026, 8:04 a.m. |
Created at: April 26, 2026, 7:47 p.m.