Triple
T2356390
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Salem (cigarette) |
E47565
|
entity |
| Predicate | hasPrimaryModeOfUse |
P1302
|
FINISHED |
| Object | inhalation of smoke |
—
|
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: inhalation of smoke | Statement: [Salem (cigarette), hasPrimaryModeOfUse, inhalation of smoke]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPrimaryModeOfUse Context triple: [Salem (cigarette), hasPrimaryModeOfUse, inhalation of smoke]
-
A.
hasPrimaryFunction
Indicates that one entity serves as the main or principal function or role of another entity.
-
B.
hasPrimaryPlatform
Indicates that one entity is designated as the main or principal platform associated with another entity.
-
C.
usedOnMode
Indicates that something is applied, operated, or functions specifically in a given mode or operational setting.
-
D.
primaryMode
chosen
Indicates the main or most commonly used method, manner, or form in which an action, process, or interaction is carried out between entities.
-
E.
appliesPrimarilyTo
Indicates that a property, rule, or characteristic is mainly relevant or intended for a particular entity or group, more than for others.
- 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.