Triple
T16407394
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gulf of Porto |
E398468
|
entity |
| Predicate | terrestrialEcosystemType |
P964
|
FINISHED |
| Object | Mediterranean shrubland |
—
|
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: Mediterranean shrubland | Statement: [Gulf of Porto, terrestrialEcosystemType, Mediterranean shrubland]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: terrestrialEcosystemType Context triple: [Gulf of Porto, terrestrialEcosystemType, Mediterranean shrubland]
-
A.
ecoregion
Indicates that one entity is located within, associated with, or belongs to the same ecological region as another entity.
-
B.
biome
Indicates the type of ecological environment or habitat in which an entity naturally exists or is situated.
-
C.
naturalRegionType
Indicates the type or category of natural region to which a given area or place belongs.
-
D.
primaryEcosystem
chosen
Indicates the main type of ecosystem in which an entity predominantly exists or operates.
-
E.
ecosystemRepresentation
Indicates that one entity serves as a model, depiction, or abstraction of an ecosystem, capturing its components, structure, or dynamics.
- 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_69d87f2950248190bc8ad9b9bebdc8c8 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e327d36b808190b6b8c412ae0d2faa |
completed | April 18, 2026, 6:42 a.m. |
| PD | Predicate disambiguation | batch_69e226fe1dd08190865c181721f8c348 |
completed | April 17, 2026, 12:26 p.m. |
Created at: April 10, 2026, 5:09 a.m.