Triple
T26190695
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Koster Islands |
E654953
|
entity |
| Predicate | marineAreaStatus |
P86884
|
FINISHED |
| Object | marine national park |
—
|
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: marine national park | Statement: [Koster Islands, marineAreaStatus, marine national park]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: marineAreaStatus Context triple: [Koster Islands, marineAreaStatus, marine national park]
-
A.
marineAreaShare
Indicates the proportion of a larger marine area that is occupied, controlled, or otherwise attributed to a specific entity.
-
B.
marineArea
Indicates a relationship where an entity is located in, associated with, or relevant to a specific marine or oceanic area.
-
C.
marineProtectionStatus
Indicates the level or type of legal or regulatory protection applied to a marine area or resource.
-
D.
marineEcoregionStatus
Indicates the current conservation or ecological condition assigned to a specific marine ecoregion.
-
E.
seaAreaDesignation
chosen
Indicates the specific legal or administrative sea area classification that has been assigned to a given marine region.
- 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_69ee5b469bc081908fe486453fdad810 |
completed | April 26, 2026, 6:36 p.m. |
| NER | Named-entity recognition | batch_69f60ca25acc81908bfe2d4ba1107748 |
completed | May 2, 2026, 2:39 p.m. |
| PD | Predicate disambiguation | batch_69f5f7fd90fc81909055b211368f9139 |
completed | May 2, 2026, 1:11 p.m. |
Created at: April 26, 2026, 8:44 p.m.