Triple

T10330291
Position Surface form Disambiguated ID Type / Status
Subject DITA E242854 entity
Predicate hasVersion P455 FINISHED
Object DITA 1.3 E242854 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: DITA 1.3 | Statement: [DITA, hasVersion, DITA 1.3]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: DITA 1.3
Context triple: [DITA, hasVersion, DITA 1.3]
  • A. DITA chosen
    DITA (Darwin Information Typing Architecture) is an XML-based standard for authoring, structuring, and publishing modular technical documentation.
  • B. DITA Open Toolkit
    DITA Open Toolkit is an open-source publishing engine that transforms DITA content into various output formats such as HTML, PDF, and EPUB.
  • C. OASIS DITA Technical Committee
    The OASIS DITA Technical Committee is the standards body within OASIS responsible for developing and maintaining the DITA XML-based architecture for structured, topic-oriented content.
  • D. ODF 1.1
    ODF 1.1 is a version of the OpenDocument Format, an open, XML-based file standard for office documents such as text, spreadsheets, and presentations.
  • E. DocBook
    DocBook is a semantic markup language, originally based on SGML and now commonly used in XML form, designed for authoring and publishing technical documentation and books in a platform-independent way.
  • 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_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_69d7fb69410c81909b33e44a04ab77d9 completed April 9, 2026, 7:18 p.m.
Created at: April 6, 2026, 11:52 a.m.