Triple

T20853
Position Surface form Disambiguated ID Type / Status
Subject World Wide Web Consortium E413 entity
Predicate hasProgram P178 FINISHED
Object WAI
WAI (Web Accessibility Initiative) is a World Wide Web Consortium (W3C) program that develops guidelines, resources, and standards to make the web accessible to people with disabilities.
 E1920 NE FINISHED

How this triple was built (4 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: WAI | Statement: [World Wide Web Consortium, hasProgram, WAI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: WAI
Context triple: [World Wide Web Consortium, hasProgram, WAI]
  • A. WAS
    WAS is the standard three-letter abbreviation used for the Washington Commanders NFL franchise.
  • B. NMTI
    NMTI is a prestigious United States presidential award that honors individuals, teams, and companies for outstanding contributions to technological innovation and advancement.
  • C. SHASS
    SHASS is the abbreviated name commonly used for the School of Humanities, Arts, and Social Sciences at academic institutions.
  • D. NLS
    NLS (oN-Line System) was an early, pioneering computer system that introduced many foundational concepts of modern computing, including the mouse, hypertext, and collaborative editing.
  • E. Lee
    Lee is a given name shared by numerous individuals across different cultures and professions.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: WAI
Triple: [World Wide Web Consortium, hasProgram, WAI]
Generated description
WAI (Web Accessibility Initiative) is a World Wide Web Consortium (W3C) program that develops guidelines, resources, and standards to make the web accessible to people with disabilities.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: WAI
Target entity description: WAI (Web Accessibility Initiative) is a World Wide Web Consortium (W3C) program that develops guidelines, resources, and standards to make the web accessible to people with disabilities.
  • A. WAS
    WAS is the standard three-letter abbreviation used for the Washington Commanders NFL franchise.
  • B. WAS
    WAS is the station code for Washington, D.C.’s main intercity and commuter rail hub, Union Station.
  • C. WSH
    WSH is the standard sports abbreviation for the Washington Commanders, the National Football League team based in the Washington, D.C. area.
  • D. NMTI
    NMTI is a prestigious United States presidential award that honors individuals, teams, and companies for outstanding contributions to technological innovation and advancement.
  • E. SHASS
    SHASS is the abbreviated name commonly used for the School of Humanities, Arts, and Social Sciences at academic institutions.
  • F. None of above. chosen

Provenance (5 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_69a240778d288190815c0052ebbbcc91 completed Feb. 28, 2026, 1:10 a.m.
NER Named-entity recognition batch_69a24669427481908b3369f090ea8edc completed Feb. 28, 2026, 1:35 a.m.
NED1 Entity disambiguation (via context triple) batch_69a248e88e588190a704e7b83d3dc07c completed Feb. 28, 2026, 1:46 a.m.
NEDg Description generation batch_69a24c29bf64819087a7b51e8a94c278 completed Feb. 28, 2026, 2 a.m.
NED2 Entity disambiguation (via description) batch_69a24cb52c9c8190a27dcb969b989649 completed Feb. 28, 2026, 2:02 a.m.
Created at: Feb. 28, 2026, 1:14 a.m.