Triple

T21983217
Position Surface form Disambiguated ID Type / Status
Subject WebBrowser E542891 entity
Predicate interpretsLanguage P108903 FINISHED
Object HTML NE NERFINISHED

How this triple was built (3 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: HTML | Statement: [WebBrowser, interpretsLanguage, HTML]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: HTML
Context triple: [WebBrowser, interpretsLanguage, HTML]
  • A. HTML chosen
    HTML (HyperText Markup Language) is the standard markup language used to structure and present content on the World Wide Web.
  • B. HTML5
    HTML5 is the fifth major version of the HyperText Markup Language standard, introducing modern web features such as semantic elements, native audio and video, and enhanced APIs for building rich, interactive web applications.
  • C. HTM
    HTM is the public transport company that operates trams and buses in and around The Hague in the Netherlands.
  • D. HTMP
    HTMP is the ICAO airport code assigned to Mpanda Airport in Tanzania.
  • E. DHTML
    DHTML (Dynamic HTML) is a web development technique that combines HTML, CSS, and JavaScript to create interactive and animated web pages that update content dynamically without reloading.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: interpretsLanguage
Context triple: [WebBrowser, interpretsLanguage, HTML]
  • A. languageOfInterpretation
    Indicates the language in which something (such as text, speech, or content) is interpreted or understood.
  • B. usesLanguageFor chosen
    Indicates that an entity employs a particular language as a tool or medium to perform some activity, function, or purpose.
  • C. languageHypothesis
    Indicates a proposed or inferred relationship concerning the language used, such as a conjecture about which language applies or how language is involved in a given context.
  • D. otherLanguage
    Indicates that an entity has or uses an additional language distinct from its primary or main language.
  • E. testLanguage
    Indicates that an entity uses or is associated with a particular language for testing or evaluation purposes.
  • F. None of above.

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_69e0c48136b081908831fa907cc02e18 completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f1270629588190aea32fbe630e4cba completed April 28, 2026, 9:30 p.m.
PD Predicate disambiguation batch_69e6f6154e408190acc5b2c278acaff4 completed April 21, 2026, 3:59 a.m.
Created at: April 16, 2026, 8:04 p.m.