Triple
T2356366
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Salem (cigarette) |
E47565
|
entity |
| Predicate | hasAdditive |
P17547
|
FINISHED |
| Object | menthol |
—
|
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: menthol | Statement: [Salem (cigarette), hasAdditive, menthol]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAdditive Context triple: [Salem (cigarette), hasAdditive, menthol]
-
A.
isAdditiveFor
Indicates that one entity can be combined with another in a way that their effects or quantities sum together to produce a cumulative result.
-
B.
canBeAugmentedWith
chosen
Indicates that one entity is capable of being enhanced, expanded, or supplemented by another entity.
-
C.
hasAdditiveGroupIsomorphicTo
Indicates that the additive group structure of one algebraic object is isomorphic (structure-preserving bijection exists) to the additive group structure of another.
-
D.
hasSupplement
Indicates that one entity provides or is associated with an additional supporting or enhancing item, resource, or component for another entity.
-
E.
hasAdditionalLetters
Indicates that one entity contains extra or more letters than another entity, beyond a specified base set or reference.
- 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_69a88a1b678c8190bce986922ba60ce0 |
completed | March 4, 2026, 7:38 p.m. |
| NER | Named-entity recognition | batch_69abcb802da08190980100444010f91e |
completed | March 7, 2026, 6:53 a.m. |
| PD | Predicate disambiguation | batch_69abc5981ce48190a3f7852d28276e11 |
completed | March 7, 2026, 6:28 a.m. |
Created at: March 4, 2026, 7:54 p.m.