Triple
T2260525
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Beloniformes |
E50027
|
entity |
| Predicate | aquariumTrade |
P37517
|
FINISHED |
| Object | ricefish and medakas kept as aquarium fishes |
—
|
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: ricefish and medakas kept as aquarium fishes | Statement: [Beloniformes, aquariumTrade, ricefish and medakas kept as aquarium fishes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: aquariumTrade Context triple: [Beloniformes, aquariumTrade, ricefish and medakas kept as aquarium fishes]
-
A.
aquariumSection
Indicates a specific section or area within an aquarium to which something (e.g., an exhibit, organism, or object) is assigned or located.
-
B.
aquariumName
Indicates that an entity has the specified name of an aquarium.
-
C.
hasAquariumType
Indicates that an entity is associated with, or classified by, a specific type or category of aquarium.
-
D.
reefType
Indicates the specific classification or category of reef associated with an entity.
-
E.
aquacultureAdvantage
Indicates that engaging in aquaculture provides a benefit, improvement, or positive outcome relative to some alternative or baseline.
- F. None of above. chosen
Provenance (4 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_69a88b01e0048190ba96431b5f990ba9 |
completed | March 4, 2026, 7:41 p.m. |
| NER | Named-entity recognition | batch_69abc2ea65288190bc8644a07a11dfa9 |
completed | March 7, 2026, 6:17 a.m. |
| PD | Predicate disambiguation | batch_69abbdb592588190ac1ef5e8c54575b1 |
completed | March 7, 2026, 5:55 a.m. |
| PDg | Predicate description generation | batch_69abc2e97eb0819084acb26cfa4e3946 |
completed | March 7, 2026, 6:17 a.m. |
Created at: March 4, 2026, 7:48 p.m.