Triple

T20685342
Position Surface form Disambiguated ID Type / Status
Subject sas E508397 entity
Predicate hasPartOf P35 FINISHED
Object ISO 639 language codes 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 639 language codes | Statement: [sas, hasPartOf, ISO 639 language codes]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ISO 639 language codes
Context triple: [sas, hasPartOf, ISO 639 language codes]
  • A. ISO 639 chosen
    ISO 639 is an international standard that defines codes for the representation of names of languages.
  • B. ISO 639-3
    ISO 639-3 is an international standard that assigns three-letter codes to uniquely identify the world’s languages, including many lesser-known and endangered ones.
  • C. ISO 639-3 Registration Authority
    The ISO 639-3 Registration Authority is the organization responsible for maintaining and updating the ISO 639-3 standard, which assigns three-letter codes to the world’s languages.
  • D. SSH Language Tags
    SSH Language Tags are standardized identifiers used within the SSH protocol to specify human languages for messages and data, enabling proper localization and internationalization.
  • E. ISO 3166-1
    ISO 3166-1 is an international standard published by ISO that defines globally recognized country codes in alpha-2, alpha-3, and numeric formats.
  • 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_69e0b4c1ed408190b72dd26b1e33f8a1 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6beabf72881909771b6c6a81276d6 completed April 21, 2026, 12:02 a.m.
Created at: April 16, 2026, 11:45 a.m.