Triple

T896112
Position Surface form Disambiguated ID Type / Status
Subject ISO 14971 E19349 entity
Predicate hasEdition P35 FINISHED
Object ISO 14971:2019 E19349 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 14971:2019 | Statement: [ISO 14971, hasEdition, ISO 14971:2019]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ISO 14971:2019
Context triple: [ISO 14971, hasEdition, ISO 14971:2019]
  • A. ISO 14971 chosen
    ISO 14971 is an international standard that specifies a systematic process for risk management of medical devices throughout their life cycle.
  • B. ISO 13485
    ISO 13485 is an international quality management standard that specifies requirements for organizations involved in the design, production, installation, and servicing of medical devices and related services.
  • C. IEC 60601-1
    IEC 60601-1 is an international standard that specifies general safety and essential performance requirements for medical electrical equipment and systems.
  • D. ISO 2108
    ISO 2108 is the international standard that defines the structure and use of the International Standard Book Number (ISBN) system for identifying books and related publications.
  • E. ISO/IEC/IEEE 29148
    ISO/IEC/IEEE 29148 is an international standard that defines best practices and processes for engineering and managing system and software requirements.
  • 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_69a4939d37188190848be3d426ebc9ae completed March 1, 2026, 7:29 p.m.
NER Named-entity recognition batch_69a4ad23d6e88190a2fb5e1e168a7b44 completed March 1, 2026, 9:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69a7cf5824608190beb2c934d4986219 completed March 4, 2026, 6:21 a.m.
Created at: March 1, 2026, 7:39 p.m.