Triple

T19997719
Position Surface form Disambiguated ID Type / Status
Subject Dave Winer E494238 entity
Predicate knownFor P22 FINISHED
Object UserLand Frontier NE NERFINISHED

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: UserLand Frontier | Statement: [Dave Winer, knownFor, UserLand Frontier]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: UserLand Frontier
Context triple: [Dave Winer, knownFor, UserLand Frontier]
  • A. UserLand Software
    UserLand Software is a software company best known for its early web publishing and blogging tools, including Frontier and Radio UserLand, which helped pioneer online content management and RSS syndication.
  • B. Frontier scripting environment chosen
    Frontier scripting environment is an early, influential scripting system and object database for the Mac, known for enabling web content automation and pioneering blogging and RSS tools.
  • C. MobileFrontend extension
    MobileFrontend extension is a MediaWiki add-on that optimizes wiki pages for viewing and editing on mobile devices by providing a dedicated mobile interface.
  • D. Domfront
    Domfront is a historic town in northwestern France known for its medieval fortress and well-preserved old quarter.
  • E. Zfone
    Zfone is a software application that provides end-to-end encrypted voice communication over IP networks using the ZRTP protocol.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69da626b2d748190886981ea90c8b2ea completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e65fe6827481909469129feb9aad91 completed April 20, 2026, 5:18 p.m.
Created at: April 11, 2026, 3:32 p.m.