Triple

T22185542
Position Surface form Disambiguated ID Type / Status
Subject ISO/IEC 2022 E548285 entity
Predicate revises P1121 FINISHED
Object ISO 2022:1986 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: ISO 2022:1986 | Statement: [ISO/IEC 2022, revises, ISO 2022:1986]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ISO 2022:1986
Context triple: [ISO/IEC 2022, revises, ISO 2022:1986]
  • A. ISO/IEC 2022 chosen
    ISO/IEC 2022 is an international standard that defines mechanisms for encoding and switching between multiple character sets within a single byte-oriented data stream.
  • B. ISO 646
    ISO 646 is an international standard for 7-bit character encodings that defines a set of basic Latin characters and allows national variants, serving as a foundation for many early computer character sets.
  • C. ISO/IEC 8859
    ISO/IEC 8859 is a family of 8-bit character encoding standards that define various single-byte coded character sets for different languages and scripts, widely used before the adoption of Unicode.
  • D. ISO 259-3
    ISO 259-3 is a part of the ISO 259 standard that specifies a system for the transliteration of Hebrew characters into Latin script.
  • E. ISO/IEC 10646
    ISO/IEC 10646 is an international standard that defines the Universal Coded Character Set (UCS), a comprehensive repertoire of characters used worldwide and closely aligned with the Unicode Standard.
  • 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_69e11e3e0c7c8190b30d278845e2497e completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f12aa823888190829368de6db4aa91 completed April 28, 2026, 9:46 p.m.
Created at: April 16, 2026, 8:35 p.m.