Triple
T16952336
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NutraSweet |
E411213
|
entity |
| Predicate | sweeteningFunction |
P125364
|
FINISHED |
| Object | replaces sugar sweetness with fewer calories |
—
|
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: replaces sugar sweetness with fewer calories | Statement: [NutraSweet, sweeteningFunction, replaces sugar sweetness with fewer calories]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sweeteningFunction Context triple: [NutraSweet, sweeteningFunction, replaces sugar sweetness with fewer calories]
-
A.
sweetening
Indicates the action or process of making something taste sweeter, often by adding a sweet substance.
-
B.
sweetenerType
Indicates the specific kind or category of sweetener associated with or used in relation to an entity.
-
C.
sweetenerVariant
Indicates that one sweetening agent is a specific type, version, or alternative form of another sweetening agent.
-
D.
isSweeterThan
Indicates that one entity has a higher level of sweetness in taste compared to another entity.
-
E.
sweetenedVersionKnownAs
Indicates that one item is a sweetened form of another and is commonly referred to by a specific name.
- 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_69d886c9c9d481909afe222093641cae |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d0197f308190af7185fc9cc7a6e9 |
completed | April 18, 2026, 6:40 p.m. |
| PD | Predicate disambiguation | batch_69e32b9aa8748190b248890aca86753d |
completed | April 18, 2026, 6:58 a.m. |
| PDg | Predicate description generation | batch_69e355722040819098830dabf207ecd6 |
completed | April 18, 2026, 9:57 a.m. |
Created at: April 10, 2026, 5:31 a.m.