Triple
T28607551
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hui cuisine |
E724093
|
entity |
| Predicate | avoidsIngredient |
P164905
|
FINISHED |
| Object | pork |
—
|
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: pork | Statement: [Hui cuisine, avoidsIngredient, pork]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: avoidsIngredient Context triple: [Hui cuisine, avoidsIngredient, pork]
-
A.
hasInactiveIngredient
Indicates that one entity contains another entity as a non-active (inactive) component or ingredient.
-
B.
isAllergenFor
Indicates that one entity acts as an allergen that can trigger an allergic reaction in another entity.
-
C.
notableIngredientRestrictionInUS
Indicates that a product or item contains an ingredient that is subject to a notable restriction, limitation, or prohibition within the United States.
-
D.
isNonAllergenic
Indicates that something does not cause allergic reactions or is free from common allergens.
-
E.
usesIngredient
Indicates that one entity employs or incorporates another entity as an ingredient in its composition or creation.
- 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_69f01d816d7c8190a1fe27e3434041dc |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_69f6562fd3488190be1acd8c526a28d2 |
completed | May 2, 2026, 7:53 p.m. |
| PD | Predicate disambiguation | batch_69f651aad92c8190b874b3b5f9f64434 |
completed | May 2, 2026, 7:34 p.m. |
| PDg | Predicate description generation | batch_69f652a3a8208190a4fdd66f34138bd2 |
completed | May 2, 2026, 7:38 p.m. |
Created at: April 28, 2026, 4:28 a.m.