Triple

T7895937
Position Surface form Disambiguated ID Type / Status
Subject ISO/IEC E183342 entity
Predicate developsStandard P73 FINISHED
Object ISO/IEC 30170 E190490 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: ISO/IEC 30170 | Statement: [ISO/IEC, developsStandard, ISO/IEC 30170]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ISO/IEC 30170
Context triple: [ISO/IEC, developsStandard, ISO/IEC 30170]
  • A. ISO/IEC 30170 chosen
    ISO/IEC 30170 is an international standard that formally specifies the Ruby programming language.
  • B. ISO/IEC 23273
    ISO/IEC 23273 is an international standard that specifies safety requirements for hydrogen-fueled road vehicles, particularly focusing on fuel cell vehicle safety.
  • C. ISO/IEC 23271
    ISO/IEC 23271 is the international standard that defines the Common Language Infrastructure (CLI), the core runtime and execution environment underlying technologies like Microsoft .NET.
  • D. ISO/IEC 14651
    ISO/IEC 14651 is an international standard that defines a universal method for ordering and comparing text strings (collation) across different languages and scripts.
  • E. ISO/IEC 19757
    ISO/IEC 19757 is an international standard, known as the Document Schema Definition Languages (DSDL) framework, that defines a modular set of languages and rules for specifying and validating the structure and content of XML documents.
  • 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_69ca828c474c8190a254d6499871eaff completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cb3a174574819084270dbb6fcbb7fe completed March 31, 2026, 3:05 a.m.
NED1 Entity disambiguation (via context triple) batch_69cb5bae4bdc8190be7db2ba3acb708a completed March 31, 2026, 5:29 a.m.
Created at: March 30, 2026, 5:01 p.m.