Triple
T27571861
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vice lipsticks |
E696057
|
entity |
| Predicate | cosmeticsCategory |
P71910
|
FINISHED |
| Object | prestige beauty |
—
|
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: prestige beauty | Statement: [Vice lipsticks, cosmeticsCategory, prestige beauty]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cosmeticsCategory Context triple: [Vice lipsticks, cosmeticsCategory, prestige beauty]
-
A.
cosmeticCategory
chosen
Indicates that one entity is classified as belonging to a particular cosmetic or beauty product category defined by the other entity.
-
B.
makeupType
Indicates the specific kind or category of makeup associated with an entity.
-
C.
includesCosmetics
Indicates that one entity contains or encompasses cosmetic products or items as part of its contents or offerings.
-
D.
facialMakeupIndicates
Indicates that the presence, style, or characteristics of facial makeup convey or signify a particular state, role, identity, or condition of an entity.
-
E.
makeupColorsInclude
Indicates that a set of makeup products or a makeup look contains or uses the specified colors.
- 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_69ef53891af88190a193c5e2a1dac9b1 |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_69f62fec821081909ae17c4c3bdcae19 |
completed | May 2, 2026, 5:10 p.m. |
| PD | Predicate disambiguation | batch_69f62c1921008190a62675a31f66a875 |
completed | May 2, 2026, 4:53 p.m. |
Created at: April 27, 2026, 1:43 p.m.