Triple

T10329234
Position Surface form Disambiguated ID Type / Status
Subject Open Web Platform E242834 entity
Predicate hasComponent P35 FINISHED
Object Web Fonts E571426 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: Web Fonts | Statement: [Open Web Platform, hasComponent, Web Fonts]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Web Fonts
Context triple: [Open Web Platform, hasComponent, Web Fonts]
  • A. Adobe Fonts
    Adobe Fonts is a subscription-based online font library and management service offering thousands of high-quality typefaces for use across desktop and web design projects.
  • B. CSS Fonts Module Level 3 chosen
    CSS Fonts Module Level 3 is a W3C specification that defines how fonts are specified, loaded, and rendered in CSS, including features like @font-face, font matching, and font feature controls.
  • C. Font Bureau
    Font Bureau is an independent type foundry known for designing and distributing a wide range of professional digital typefaces used in publishing, branding, and user interfaces.
  • D. Font Book
    Font Book is a macOS application used to manage, preview, install, and organize fonts on a Mac.
  • E. OpenType font technology
    OpenType font technology is a scalable, cross-platform font format developed by Microsoft and Adobe that supports advanced typographic features such as ligatures, contextual substitutions, and complex script shaping.
  • 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_69d381af787481908bc401325c760a88 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4d7cfd54c8190b6f88598339536d1 completed April 7, 2026, 10:09 a.m.
NED1 Entity disambiguation (via context triple) batch_69d71db4a8dc81909adb2a044e74fd6b completed April 9, 2026, 3:32 a.m.
Created at: April 6, 2026, 11:52 a.m.