Triple
T200821
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Solomon Islands rain forests |
E4099
|
entity |
| Predicate | hasSoilType |
P1675
|
FINISHED |
| Object | weathered tropical soils |
—
|
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: weathered tropical soils | Statement: [Solomon Islands rain forests, hasSoilType, weathered tropical soils]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSoilType Context triple: [Solomon Islands rain forests, hasSoilType, weathered tropical soils]
-
A.
hasSoil
chosen
Indicates that one entity possesses, contains, or is associated with a particular type or instance of soil.
-
B.
soilPreference
Indicates the type or condition of soil that an entity prefers or is best suited to grow or exist in.
-
C.
hasRockType
Indicates that an entity is composed of, characterized by, or associated with a specific type of rock.
-
D.
vegetationType
Indicates the specific kind or category of plant cover or flora that characterizes a given area or environment.
-
E.
hasAreaType
Indicates that an entity is associated with a specific kind or classification of area (e.g., urban, rural, coastal).
- 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_69a254bca59881909a15e1496f1508c7 |
completed | Feb. 28, 2026, 2:36 a.m. |
| NER | Named-entity recognition | batch_69a25c2ead8481909996042efcae5e9d |
completed | Feb. 28, 2026, 3:08 a.m. |
| PD | Predicate disambiguation | batch_69a25b4a0d448190a6fa6aeb30dc7e13 |
completed | Feb. 28, 2026, 3:04 a.m. |
Created at: Feb. 28, 2026, 2:44 a.m.