Triple
T23675820
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sol over Gudhjem |
E584869
|
entity |
| Predicate | usesLocalProduct |
P108862
|
FINISHED |
| Object | Bornholm smoked herring |
—
|
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: Bornholm smoked herring | Statement: [Sol over Gudhjem, usesLocalProduct, Bornholm smoked herring]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesLocalProduct Context triple: [Sol over Gudhjem, usesLocalProduct, Bornholm smoked herring]
-
A.
usesProductFrom
Indicates that one entity makes use of or employs a product that originates from or is provided by another entity.
-
B.
usesProduct
Indicates that one entity makes use of, applies, or employs a particular product.
-
C.
usesLocalProduce
chosen
Indicates that one entity obtains and incorporates agricultural products sourced from nearby or locally based producers.
-
D.
isLocalQuantity
Indicates that a quantity is specific to a particular context, location, or subsystem rather than being globally applicable.
-
E.
isLocalOn
Indicates that something resides or operates on a specific local device, system, or node rather than remotely.
- 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_69e24901f7c08190909fd727632e823d |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b4f2e35c8190ada29694e2cbed37 |
completed | April 29, 2026, 7:36 a.m. |
| PD | Predicate disambiguation | batch_69f118dd13008190a8799b4e9cadbd79 |
completed | April 28, 2026, 8:30 p.m. |
Created at: April 17, 2026, 6:51 p.m.