Triple

T20281406
Position Surface form Disambiguated ID Type / Status
Subject Phoenix E503151 entity
Predicate uses P98 FINISHED
Object Cowboy web server E1282064 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: Cowboy web server | Statement: [Phoenix, uses, Cowboy web server]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cowboy web server
Context triple: [Phoenix, uses, Cowboy web server]
  • A. Cowboy web server chosen
    Cowboy web server is a small, fast, and modern HTTP server written in Erlang, commonly used in the Elixir ecosystem for building scalable web applications.
  • B. NCSA HTTPd
    NCSA HTTPd was one of the earliest and most influential web server software programs, developed at the National Center for Supercomputing Applications and serving as a foundation for later servers like Apache.
  • C. The Rack
    The Rack is a 1956 courtroom drama film about the psychological and moral aftermath of a Korean War veteran’s imprisonment and alleged collaboration with the enemy.
  • D. WEBrick
    WEBrick is a Ruby standard library HTTP server toolkit commonly used for developing and testing web applications.
  • E. Koa web framework
    Koa is a minimalist, modern Node.js web framework designed by TJ Holowaychuk to provide a smaller, more expressive, and robust foundation for web applications and APIs using async functions.
  • 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_69e0b4b0e79c8190bd61f22ef1329fa8 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6768e9f0881909c8fe8772dafd468 completed April 20, 2026, 6:55 p.m.
NED1 Entity disambiguation (via context triple) batch_6a085a25e5f08190b11cbcbdda42113b completed May 16, 2026, 11:51 a.m.
Created at: April 16, 2026, 10:38 a.m.