Triple
T28553769
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tunisian cuisine |
E722950
|
entity |
| Predicate | notableCondiment |
P102161
|
FINISHED |
| Object | harissa |
—
|
NE NERFINISHED |
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: harissa | Statement: [Tunisian cuisine, notableCondiment, harissa]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableCondiment Context triple: [Tunisian cuisine, notableCondiment, harissa]
-
A.
isTypicallyGarnishedWith
Indicates that one item is commonly used as a garnish or decorative finishing element for another.
-
B.
typicalSpices
chosen
Indicates that certain spices are commonly or characteristically used in association with a particular dish, cuisine, or ingredient.
-
C.
sauceType
Indicates the specific kind or category of sauce associated with an item or dish.
-
D.
seasoningType
Indicates the specific kind or category of seasoning associated with an item or preparation.
-
E.
usesIngredient
Indicates that one entity employs or incorporates another entity as an ingredient in its composition or creation.
- 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_69f01a60204481909af1bb76247b8221 |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_6a0136e4af808190b529d324bbf0c5d9 |
completed | May 11, 2026, 1:54 a.m. |
| PD | Predicate disambiguation | batch_6a01369141c4819091cb8064913a44ca |
completed | May 11, 2026, 1:53 a.m. |
Created at: April 28, 2026, 3:44 a.m.