Triple
T8945689
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Salmon |
E213215
|
entity |
| Predicate | preparedAs |
P77270
|
FINISHED |
| Object | smoked salmon |
—
|
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: smoked salmon | Statement: [Salmon, preparedAs, smoked salmon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: preparedAs Context triple: [Salmon, preparedAs, smoked salmon]
-
A.
preparedAt
Indicates the time or place at which something was prepared or made ready.
-
B.
preparedFor
Indicates that one entity has been made ready, equipped, or arranged in anticipation of use by or in connection with another entity.
-
C.
preparesFor
Indicates that one entity is used, designed, or undertaken in order to get another entity ready for a future event, state, or activity.
-
D.
preparationBy
Indicates that one entity is created, assembled, or made ready through the actions or processes performed by another entity.
-
E.
isPreparedAs
chosen
Indicates that one entity is made ready, arranged, or configured in a particular way or form as specified by another entity.
- 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_69ca839843408190a39069a029a89f15 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc66db998c8190999a7a686bbdda1f |
completed | April 1, 2026, 12:29 a.m. |
| PD | Predicate disambiguation | batch_69cc5ed5267c8190a43feb2a2f3df1ec |
completed | March 31, 2026, 11:55 p.m. |
Created at: March 30, 2026, 6:59 p.m.