Triple
T36083635
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | CCAMLR Conservation Measure 91-05 |
E1043718
|
entity |
| Predicate | appliesToOcean |
P6297
|
FINISHED |
| Object | Southern Ocean |
—
|
NE NERFINISHED |
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: Southern Ocean | Statement: [CCAMLR Conservation Measure 91-05, appliesToOcean, Southern Ocean]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: appliesToOcean Context triple: [CCAMLR Conservation Measure 91-05, appliesToOcean, Southern Ocean]
-
A.
isOceanic
Indicates that something belongs to, originates from, or is characteristic of the ocean or oceanic regions.
-
B.
appliesToSeaArea
chosen
Indicates that something (such as a rule, restriction, or designation) is relevant or valid within a specified sea area.
-
C.
hasOceanType
Indicates that a body of water is classified as belonging to a particular type of ocean or oceanic category.
-
D.
oceanToOcean
Indicates a relationship where something extends, connects, or operates from one ocean to another.
-
E.
hasOcean
Indicates that a geographic region, country, or landmass is bordered by or directly adjacent to a particular ocean.
- 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_69f76e3154908190a6f702671c2bea08 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69ff63225b6481909217ad11b4f7d3ba |
completed | May 9, 2026, 4:38 p.m. |
| PD | Predicate disambiguation | batch_69ff60e0882c819085d097010db43ee0 |
completed | May 9, 2026, 4:29 p.m. |
Created at: May 3, 2026, 4:08 p.m.