Triple
T23167031
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Algerian Basin |
E578738
|
entity |
| Predicate | hasOceanFeature |
P77269
|
FINISHED |
| Object | Algerian eddies |
—
|
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: Algerian eddies | Statement: [Algerian Basin, hasOceanFeature, Algerian eddies]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOceanFeature Context triple: [Algerian Basin, hasOceanFeature, Algerian eddies]
-
A.
hasOceanType
Indicates that a body of water is classified as belonging to a particular type of ocean or oceanic category.
-
B.
hasOcean
Indicates that a geographic region, country, or landmass is bordered by or directly adjacent to a particular ocean.
-
C.
hasMaritimeFeature
chosen
Indicates that one entity possesses, contains, or is characterized by a maritime-related feature such as a sea, coast, harbor, or other oceanic element.
-
D.
hasNearbyMarineFeature
Indicates that one entity is located close to a marine geographic feature associated with the other entity.
-
E.
oceanPresence
Indicates that an entity is located in, adjacent to, or significantly influenced by an 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_69e245fc75348190a0288401044c8af8 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18f2c923c81908b58811fffdcf932 |
completed | April 29, 2026, 4:55 a.m. |
| PD | Predicate disambiguation | batch_69ef89ff76808190808ee4ad9dea776b |
completed | April 27, 2026, 4:08 p.m. |
Created at: April 17, 2026, 4:03 p.m.