Triple
T11216363
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Western Sweden |
E265447
|
entity |
| Predicate | seafoodSpeciality |
P79990
|
FINISHED |
| Object | shrimp |
—
|
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: shrimp | Statement: [Western Sweden, seafoodSpeciality, shrimp]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: seafoodSpeciality Context triple: [Western Sweden, seafoodSpeciality, shrimp]
-
A.
seafoodSpecialty
chosen
Indicates that one entity specializes in preparing, serving, or producing seafood as a primary focus or notable expertise.
-
B.
fisheriesProduct
Indicates that something is a product derived from fishing activities or the harvesting of aquatic organisms.
-
C.
aquacultureProduct
Indicates that something is a product derived from aquaculture activities, such as the farming or cultivation of aquatic organisms.
-
D.
salmonType
Indicates that one entity is classified as a specific type or variety of salmon in relation to another entity.
-
E.
fisheryType
Indicates the specific category or kind of fishery associated with an entity, such as its operational or regulatory classification.
- 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_69d6aac59460819089b9848b27f57848 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e8e8eef48190932a85784ce15c86 |
completed | April 9, 2026, 5:59 p.m. |
| PD | Predicate disambiguation | batch_69d75cfbbb188190861efd5d94fe27da |
completed | April 9, 2026, 8:02 a.m. |
Created at: April 8, 2026, 9:30 p.m.