Triple

T23332578
Position Surface form Disambiguated ID Type / Status
Subject STAR File syntax E591485 entity
Predicate fullName P16 FINISHED
Object Self-defining Text Archive and Retrieval file syntax NE NERFINISHED

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: Self-defining Text Archive and Retrieval file syntax | Statement: [STAR File syntax, fullName, Self-defining Text Archive and Retrieval file syntax]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Self-defining Text Archive and Retrieval file syntax
Context triple: [STAR File syntax, fullName, Self-defining Text Archive and Retrieval file syntax]
  • A. STAR File syntax chosen
    STAR File syntax is a flexible, text-based data format used in crystallography and related sciences to store structured experimental and structural information in a machine-readable way.
  • B. Scribe text processing system
    The Scribe text processing system is an early, influential document preparation and formatting program developed by Brian Reid that pioneered many concepts later used in systems like LaTeX.
  • C. Maschinelles Austauschformat für Bibliotheken
    Maschinelles Austauschformat für Bibliotheken (MAB) is a German machine-readable data exchange format historically used by libraries to encode and share bibliographic and authority records.
  • D. Character repertoire description language (CREPDL)
    Character repertoire description language (CREPDL) is an ISO/IEC 19757-7 standard for formally specifying and validating sets of permitted characters in XML and related document formats.
  • E. Darwin Information Typing Architecture
    Darwin Information Typing Architecture (DITA) is an XML-based, topic-oriented architecture and standard for authoring, organizing, and publishing technical content in a modular and reusable way.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e25d20156c81908c5c53195bd9c738 completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f197eecc5c81908089eb43bc701196 completed April 29, 2026, 5:32 a.m.
Created at: April 17, 2026, 5:15 p.m.