Triple

T691256
Position Surface form Disambiguated ID Type / Status
Subject Herbert Bayer E13396 entity
Predicate designed P184 FINISHED
Object Universal typeface E84307 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: Universal typeface | Statement: [Herbert Bayer, designed, Universal typeface]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Universal typeface
Context triple: [Herbert Bayer, designed, Universal typeface]
  • A. Universal typeface chosen
    Universal typeface is a minimalist, geometric sans-serif typeface designed by Bauhaus artist Herbert Bayer as an experimental attempt to create a simplified, universal writing system.
  • B. Johnston typeface
    Johnston typeface is a humanist sans-serif typeface designed in the early 20th century by Edward Johnston, best known as the iconic lettering used across the London Underground network.
  • C. Caslon
    Caslon is a casual, contemporary women's clothing and footwear brand known for its comfortable basics and everyday wardrobe staples, often sold at Nordstrom.
  • D. TMU Bold
    TMU Bold is the varsity athletics program representing Toronto Metropolitan University in intercollegiate sports competitions.
  • E. Unicode Consortium
    The Unicode Consortium is a non-profit organization that standardizes the representation of text and symbols in digital systems worldwide through the Unicode Standard.
  • 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_69a4933e0f98819097d22766c49b61b8 completed March 1, 2026, 7:27 p.m.
NER Named-entity recognition batch_69a4a0aebde88190a49d421477713103 completed March 1, 2026, 8:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69a637514c9081909938d0801f071fea completed March 3, 2026, 1:20 a.m.
Created at: March 1, 2026, 7:36 p.m.