Triple

T2648916
Position Surface form Disambiguated ID Type / Status
Subject Maye Haldeman E53849 entity
Predicate hasModeledFor P17880 FINISHED
Object CoverGirl E51749 NE FINISHED

How this triple was built (3 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: CoverGirl | Statement: [Maye Haldeman, hasModeledFor, CoverGirl]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: CoverGirl
Context triple: [Maye Haldeman, hasModeledFor, CoverGirl]
  • A. CoverGirl chosen
    CoverGirl is a major American cosmetics brand known for its mass-market makeup products and high-profile celebrity spokesmodels.
  • B. Maybelline New York
    Maybelline New York is a major American cosmetics and beauty brand known worldwide for its mass-market makeup products.
  • C. Revlon
    Revlon is a major American cosmetics, skincare, fragrance, and personal care company known for its mass-market beauty products and global brand presence.
  • D. Essie
    Essie is a popular nail polish and nail care brand known for its wide range of fashion-forward colors and salon-quality formulas.
  • E. NYX Professional Makeup
    NYX Professional Makeup is a popular, affordable cosmetics brand known for its wide range of highly pigmented, trend-driven makeup products favored by both professionals and everyday consumers.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasModeledFor
Context triple: [Maye Haldeman, hasModeledFor, CoverGirl]
  • A. hasModelledFor chosen
    Indicates that one entity has served as a model for another entity, typically in a professional or representational context such as art, photography, or fashion.
  • B. isModelOf
    Indicates that one entity serves as a representation or abstraction that captures the structure or behavior of another entity.
  • C. hasRealModel
    Indicates that an abstract, theoretical, or simplified entity is associated with a corresponding concrete or physically instantiated model in the real world.
  • D. hasStudyModel
    Indicates that an entity is associated with, or defined by, a particular study model used for analysis, simulation, or representation.
  • E. usedToModel
    Indicates that one entity serves as a model or representation for another entity, typically for purposes of analysis, simulation, or understanding.
  • F. None of above.

Provenance (4 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_69ab495e192081909c77b622e8e7e15a completed March 6, 2026, 9:38 p.m.
NER Named-entity recognition batch_69abd91b4b3c81908571e85a1621dfc5 completed March 7, 2026, 7:51 a.m.
NED1 Entity disambiguation (via context triple) batch_69af98c944548190a8dbe9b81045e97b completed March 10, 2026, 4:06 a.m.
PD Predicate disambiguation batch_69abd814298c8190952f05aed43f6bb8 completed March 7, 2026, 7:47 a.m.
Created at: March 6, 2026, 9:53 p.m.