Triple

T11559697
Position Surface form Disambiguated ID Type / Status
Subject Even Better E274108 entity
Predicate includes P1393 FINISHED
Object Even Better foundation E274108 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: Even Better foundation | Statement: [Even Better, includes, Even Better foundation]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Even Better foundation
Context triple: [Even Better, includes, Even Better foundation]
  • A. Even Better chosen
    Even Better is a Clinique skincare and makeup line focused on improving skin tone, radiance, and discoloration.
  • B. The Better Me
    "The Better Me" is a motivational track from the podcast "On Purpose" that focuses on personal growth and self-improvement.
  • C. Fit Me foundation
    Fit Me foundation is a popular Maybelline New York makeup line known for its wide shade range and natural, skin-like finish.
  • D. Do Better
    "Do Better" is a reflective and introspective hip-hop track by Ab-Soul that grapples with personal growth, grief, and self-improvement.
  • E. Better and Worse
    "Better and Worse" is a song by the band On Purpose.
  • 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_69d6aae4dfa48190a3ab0b19a159a3c5 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d88a899d4481909a3bce3147763b51 completed April 10, 2026, 5:28 a.m.
NED1 Entity disambiguation (via context triple) batch_69e6e88b84d48190948243646bb5fd2b completed April 21, 2026, 3:01 a.m.
Created at: April 8, 2026, 9:37 p.m.