Triple
T34488381
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | pastirma |
E885394
|
entity |
| Predicate | consumptionRestriction |
P179416
|
FINISHED |
| Object | not suitable for vegetarians |
—
|
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: not suitable for vegetarians | Statement: [pastirma, consumptionRestriction, not suitable for vegetarians]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: consumptionRestriction Context triple: [pastirma, consumptionRestriction, not suitable for vegetarians]
-
A.
notableIngredientRestrictionInUS
Indicates that a product or item contains an ingredient that is subject to a notable restriction, limitation, or prohibition within the United States.
-
B.
isTypicallyConsumedFrom
Indicates that one entity is most commonly eaten or drunk using, contained in, or taken from the other entity.
-
C.
mayHaveRestriction
Indicates that an entity can be subject to one or more limitations, conditions, or constraints, though such restrictions are not necessarily present.
-
D.
intendedConsumption
Indicates that one entity is meant or designed to be consumed or used up by another entity.
-
E.
eatingPermitted
Indicates that an entity is allowed or authorized to eat in a given context or situation.
- 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_69f349c947fc81909d30b53c194d6ea1 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f720cc1bfc8190a16118e3af8e9316 |
completed | May 3, 2026, 10:17 a.m. |
| PD | Predicate disambiguation | batch_69f71cc6397881909aaad37a9daa8a7e |
completed | May 3, 2026, 10 a.m. |
| PDg | Predicate description generation | batch_69f71fb0172c81908f23e95ff16b0dec |
completed | May 3, 2026, 10:13 a.m. |
Created at: May 1, 2026, 2:01 a.m.