Triple

T6991544
Position Surface form Disambiguated ID Type / Status
Subject UTF-8 E162096 entity
Predicate specifiedBy P21520 FINISHED
Object Unicode Standard E598531 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: Unicode Standard | Statement: [UTF-8, specifiedBy, Unicode Standard]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Unicode Standard
Context triple: [UTF-8, specifiedBy, Unicode Standard]
  • A. Unicode Standard chosen
    The Unicode Standard is a universal character encoding system that assigns unique code points to text and symbols from virtually all writing systems, enabling consistent digital representation and interchange of text worldwide.
  • B. Unicode Technical Standards
    Unicode Technical Standards are a collection of specifications that define how text and related data are consistently encoded, represented, and processed across different platforms and languages in the Unicode ecosystem.
  • C. Unicode Technical Standard #10
    Unicode Technical Standard #10 is the specification that defines the Unicode Collation Algorithm, providing a standardized method for comparing and sorting Unicode text across languages and platforms.
  • D. Unicode Technical Standard #35
    Unicode Technical Standard #35 is a Unicode Consortium specification that defines the Locale Data Markup Language (LDML) and related mechanisms for internationalization, including formatting of dates, times, numbers, and other locale-sensitive data.
  • E. Unicode Standard Annex #38
    Unicode Standard Annex #38 is a technical report that defines the Unicode Han Database (Unihan), specifying data fields and properties for East Asian ideographs used in the Unicode Standard.
  • 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: specifiedBy
Context triple: [UTF-8, specifiedBy, Unicode Standard]
  • A. specifiedFor
    Indicates that something is designated or intended to be used for a particular entity, purpose, or context.
  • B. determinedBy
    Indicates that one entity’s state, value, or outcome is decided, controlled, or fully specified by another entity.
  • C. firstSpecified
    Indicates that the subject is the earliest or initial entity explicitly designated or chosen among a set of specified entities.
  • D. specType
    Indicates the specific type or category of a specification that an entity is associated with.
  • E. designSpecifiedBy chosen
    Indicates that the design or specification of one entity is defined, authored, or determined by 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_69c68856d7808190ab33ee914640281b completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6dbc1f63c8190837cfd71cf5ed613 completed March 27, 2026, 7:34 p.m.
NED1 Entity disambiguation (via context triple) batch_69c761d6ed5481909ccf1650fe6dc747 completed March 28, 2026, 5:06 a.m.
PD Predicate disambiguation batch_69c6d7c4a18881908d267137daed828b completed March 27, 2026, 7:17 p.m.
Created at: March 27, 2026, 2:32 p.m.