Triple

T12562052
Position Surface form Disambiguated ID Type / Status
Subject XeTeX E295373 entity
Predicate relatedTo P37 FINISHED
Object LuaTeX E308572 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: LuaTeX | Statement: [XeTeX, relatedTo, LuaTeX]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: LuaTeX
Context triple: [XeTeX, relatedTo, LuaTeX]
  • A. LuaTeX chosen
    LuaTeX is an extended TeX-based typesetting engine that embeds the Lua scripting language to provide powerful programmability and advanced typographic features beyond traditional LaTeX workflows.
  • B. XeTeX
    XeTeX is an extension of the TeX typesetting system that natively supports Unicode and modern font technologies like OpenType, enabling high-quality multilingual and typographically advanced document production.
  • C. pdfTeX
    pdfTeX is an extended version of Knuth’s TeX engine that can directly generate PDF output and offers advanced typographic and microtypographic features.
  • D. LaTeX3
    LaTeX3 is the next-generation, experimental programming layer and macro system for LaTeX, designed to provide a more consistent, modular, and extensible foundation for document preparation.
  • E. upTeX
    upTeX is a Japanese-enabled TeX engine that extends pTeX with full Unicode support for typesetting multilingual documents, especially those containing Japanese text.
  • 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_69d6ad9cac2c81908e8a7bed82d1e21d completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d95494ae1c81908b9ee14b8ef92a65 completed April 10, 2026, 7:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6558da7e0819086860bfaf394e2d8 completed May 2, 2026, 7:50 p.m.
Created at: April 8, 2026, 11:48 p.m.