Triple
T1325284
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maybelline New York |
E28311
|
entity |
| Predicate | marketingChannel |
P18370
|
FINISHED |
| Object | television advertising |
—
|
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: television advertising | Statement: [Maybelline New York, marketingChannel, television advertising]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: marketingChannel Context triple: [Maybelline New York, marketingChannel, television advertising]
-
A.
marketingNameOf
Indicates that one entity is the marketing or brand name used to promote or refer to another entity.
-
B.
marketingAs
Indicates that one entity is being presented, promoted, or branded to others as if it were another specified entity, role, or category.
-
C.
marketingUse
chosen
Indicates that something is used for marketing purposes, such as promotion, advertising, or brand communication.
-
D.
mediaMarket
Indicates a relationship where a media outlet or content provider serves, targets, or operates within a particular geographic or demographic market.
-
E.
marketingModel
Indicates a relationship where an entity uses or is associated with a specific marketing model, framework, or strategy to guide promotional or market-related decisions.
- 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_69a498540a2481909e807a762280d3ba |
completed | March 1, 2026, 7:49 p.m. |
| NER | Named-entity recognition | batch_69a4c19e81c0819092f85201ae34422a |
completed | March 1, 2026, 10:45 p.m. |
| PD | Predicate disambiguation | batch_69a4beedb49c8190beb5b85cdda05013 |
completed | March 1, 2026, 10:34 p.m. |
Created at: March 1, 2026, 7:55 p.m.