Triple

T10330302
Position Surface form Disambiguated ID Type / Status
Subject DITA E242854 entity
Predicate outputFormats P38824 FINISHED
Object HTML E1918 NE FINISHED

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: [DITA, outputFormats, HTML]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: HTML
Context triple: [DITA, outputFormats, 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: outputFormats
Context triple: [DITA, outputFormats, HTML]
  • A. previousFormats
    Indicates that an entity has had one or more earlier or prior formats or versions it existed in before its current form.
  • B. packageFormat
    Indicates the format or type in which a package is structured, encoded, or delivered.
  • C. containerFormats
    Indicates that one entity serves as a container or packaging format used to hold, encapsulate, or structure the contents of another entity.
  • D. operatesInFormat chosen
    Indicates that an entity functions, performs its role, or is carried out using a specified format.
  • E. includeFormat
    Indicates that one entity contains or specifies the format or representation type of another entity.
  • F. None of above.

Provenance (4 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_69d4d7fb77348190ac8ff887f6f03450 completed April 7, 2026, 10:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69d71db4a8dc81909adb2a044e74fd6b completed April 9, 2026, 3:32 a.m.
PD Predicate disambiguation batch_69d4d1f760e88190abea6dcc4f04f2c1 completed April 7, 2026, 9:44 a.m.
Created at: April 6, 2026, 11:52 a.m.