Triple
T17076475
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sprite Zero Sugar |
E414358
|
entity |
| Predicate | hasPreservative |
P56320
|
FINISHED |
| Object | potassium benzoate |
—
|
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: potassium benzoate | Statement: [Sprite Zero Sugar, hasPreservative, potassium benzoate]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPreservative Context triple: [Sprite Zero Sugar, hasPreservative, potassium benzoate]
-
A.
containsAdditives
chosen
Indicates that one entity includes or is composed of additional substances or ingredients beyond its primary or original components.
-
B.
coFormulatedWith
Indicates that one entity is formulated together with another as part of the same combined product or composition.
-
C.
hasHealthWarningOnPackaging
Indicates that an item’s packaging displays a health-related warning message or symbol.
-
D.
containsAllergenicCompound
Indicates that the subject entity includes one or more compounds known to cause allergic reactions.
-
E.
hasFragrance
Indicates that one entity possesses or emits a particular scent or aroma associated with 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_69d886cef44c8190ba56c44b4e863e64 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3dbc559388190b685504cca6ed62b |
completed | April 18, 2026, 7:30 p.m. |
| PD | Predicate disambiguation | batch_69e35d642f74819098c014135e249b27 |
completed | April 18, 2026, 10:31 a.m. |
Created at: April 10, 2026, 5:34 a.m.