Triple
T14117109
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vicks |
E339800
|
entity |
| Predicate | brandOf |
P1500
|
FINISHED |
| Object | Vicks inhaler |
E339800
|
NE 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: Vicks inhaler | Statement: [Vicks, brandOf, Vicks inhaler]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Vicks inhaler Context triple: [Vicks, brandOf, Vicks inhaler]
-
A.
Vicks
chosen
Vicks is a well-known over-the-counter healthcare brand recognized for its cold, cough, and flu relief products such as VapoRub and cough syrups.
-
B.
Inhaler
Inhaler is an Irish rock band fronted by vocalist and guitarist Elijah Hewson, known for its melodic, anthemic sound and rising prominence in contemporary alternative music.
-
C.
Snoline
Snoline is a Lindsay Corporation brand known for its road safety and traffic management products, such as lane markings and safety systems.
-
D.
Mucinex
Mucinex is an over-the-counter expectorant medication, best known for helping relieve chest congestion by thinning and loosening mucus.
-
E.
L&M Menthol
L&M Menthol is a menthol-flavored variant of the L&M cigarette brand, offering a cooler, minty smoking experience.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d81c6a95b481909e39111e0c1f31ee |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de6010a03c81909f5f160f8d1fa8fa |
completed | April 14, 2026, 3:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fcd0baa328819099511dfa7b9666d3 |
completed | May 7, 2026, 5:49 p.m. |
Created at: April 9, 2026, 10:22 p.m.