Triple
T8088805
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Playa de la Cocina |
E188801
|
entity |
| Predicate | hasWindExposure |
P68425
|
FINISHED |
| Object | moderate trade winds but sheltered by terrain |
—
|
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: moderate trade winds but sheltered by terrain | Statement: [Playa de la Cocina, hasWindExposure, moderate trade winds but sheltered by terrain]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasWindExposure Context triple: [Playa de la Cocina, hasWindExposure, moderate trade winds but sheltered by terrain]
-
A.
hasWindPattern
Indicates that one entity exhibits, is characterized by, or is associated with a particular pattern of wind behavior.
-
B.
isOutdoor
Indicates that an entity or activity takes place outside, in an open-air or non-enclosed environment.
-
C.
usedWhenWindFrom
Indicates that something is employed or activated under conditions where the wind is coming from a specified direction.
-
D.
exteriorFeature
Indicates a relationship where one entity serves as an external or outward-facing feature, element, or characteristic of another entity.
-
E.
typicalWindStrength
chosen
Indicates the usual or characteristic intensity of wind associated with something, such as a place, time, or condition.
- 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_69ca82b7b3e88190b9041ab0ef28b3cb |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb421c717c819089dd88c30a6401aa |
completed | March 31, 2026, 3:40 a.m. |
| PD | Predicate disambiguation | batch_69cb04a14cd88190a79ed26cbeec1c33 |
completed | March 30, 2026, 11:17 p.m. |
Created at: March 30, 2026, 5:29 p.m.