Triple
T5632568
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hypnôse Mascara |
E147867
|
entity |
| Predicate | brandLine |
P64700
|
FINISHED |
| Object | Lancôme Hypnôse line |
E27682
|
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: Lancôme Hypnôse line | Statement: [Hypnôse Mascara, brandLine, Lancôme Hypnôse line]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lancôme Hypnôse line Context triple: [Hypnôse Mascara, brandLine, Lancôme Hypnôse line]
-
A.
Lancôme
chosen
Lancôme is a French luxury cosmetics and skincare brand renowned for its high-end perfumes, makeup, and beauty products.
-
B.
Guerlain
Guerlain is a historic French luxury perfume, cosmetics, and skincare house renowned for its iconic fragrances and high-end beauty products.
-
C.
Yves Saint Laurent Beauté
Yves Saint Laurent Beauté is a luxury cosmetics and fragrance brand known for its high-end makeup, skincare, and iconic perfumes.
-
D.
Maybelline New York
Maybelline New York is a major American cosmetics and beauty brand known worldwide for its mass-market makeup products.
-
E.
Biotherm
Biotherm is a French skincare brand known for its use of aquatic ingredients and scientifically driven formulas for face and body care.
- 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_69c00907bc8881909ed760d3ed73ef35 |
completed | March 22, 2026, 3:21 p.m. |
| NER | Named-entity recognition | batch_69c0225e8e848190a9ccd48fc0d74e5c |
completed | March 22, 2026, 5:09 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c05a1666d88190af4c1890247f897d |
completed | March 22, 2026, 9:07 p.m. |
Created at: March 22, 2026, 3:41 p.m.