Triple

T7762036
Position Surface form Disambiguated ID Type / Status
Subject Thomas Lyle Williams E176044 entity
Predicate founded P104 FINISHED
Object Maybelline E28311 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: Maybelline | Statement: [Thomas Lyle Williams, founded, Maybelline]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Maybelline
Context triple: [Thomas Lyle Williams, founded, Maybelline]
  • A. Maybelline New York chosen
    Maybelline New York is a major American cosmetics and beauty brand known worldwide for its mass-market makeup products.
  • B. Revlon
    Revlon is a major American cosmetics, skincare, fragrance, and personal care company known for its mass-market beauty products and global brand presence.
  • C. Benefit Cosmetics
    Benefit Cosmetics is a San Francisco–born beauty brand known for its playful packaging and bestselling brow and complexion products, and is part of the luxury group LVMH.
  • D. Armani Beauty
    Armani Beauty is the cosmetics and fragrance line of the Giorgio Armani fashion house, known for its luxurious makeup, skincare, and signature perfumes.
  • E. Essie
    Essie is a popular nail polish and nail care brand known for its wide range of fashion-forward colors and salon-quality formulas.
  • 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_69c69962923c8190ac74d28b4f9fe0a0 completed March 27, 2026, 2:51 p.m.
NER Named-entity recognition batch_69c70404c2108190ad2b900ac9bf582b completed March 27, 2026, 10:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8c7d658888190af97b83127086a2b completed March 29, 2026, 6:33 a.m.
Created at: March 27, 2026, 4:09 p.m.