Triple

T12900032
Position Surface form Disambiguated ID Type / Status
Subject The LaTeX Companion E308587 entity
Predicate relatedTo P37 FINISHED
Object The LaTeX Web Companion E308587 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: The LaTeX Web Companion | Statement: [The LaTeX Companion, relatedTo, The LaTeX Web Companion]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: The LaTeX Web Companion
Context triple: [The LaTeX Companion, relatedTo, The LaTeX Web Companion]
  • A. LaTeX Companion chosen
    The LaTeX Companion is a comprehensive reference book that explains advanced LaTeX features, packages, and best practices for typesetting professional-quality documents.
  • B. Isabelle document preparation system
    The Isabelle document preparation system is a tool integrated with the Isabelle proof assistant that supports the structured authoring and typesetting of formal proofs and related documents, typically producing high-quality LaTeX/PDF output.
  • C. LaTeX User’s Guide and Reference Manual
    The LaTeX User’s Guide and Reference Manual is a comprehensive book that explains how to use the LaTeX typesetting system, covering both introductory tutorials and detailed reference material for commands and packages.
  • D. LaTeX
    LaTeX is a widely used, high-quality typesetting system particularly popular in academia for producing technical and scientific documents with precise control over layout and mathematical notation.
  • E. CWEB literate programming system
    The CWEB literate programming system is a software tool created by Donald E. Knuth (with Silvio Levy) that integrates C or C++ source code with richly formatted documentation to produce both compilable programs and high-quality typeset descriptions.
  • 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_69d7bdf7c1f0819098102569a8d8cbf5 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d97180ee708190b60a3e58c42f764f completed April 10, 2026, 9:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6a56189b081909ed838addcb6d265 completed May 3, 2026, 1:31 a.m.
Created at: April 9, 2026, 5:40 p.m.