Triple

T19019430
Position Surface form Disambiguated ID Type / Status
Subject BSI Group E465443 entity
Predicate standardPrefix P7276 FINISHED
Object BS ISO 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: BS ISO | Statement: [BSI Group, standardPrefix, BS ISO]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: BS ISO
Context triple: [BSI Group, standardPrefix, BS ISO]
  • A. ISO
    ISO is a European Space Agency infrared space telescope that operated in the mid-1990s to study the universe at infrared wavelengths.
  • B. ISO
    ISO is a widely used optical disc image file format that encapsulates the complete contents and structure of CD, DVD, or Blu-ray media in a single file.
  • C. ISO standards chosen
    ISO standards are internationally agreed-upon specifications and guidelines developed by the International Organization for Standardization to ensure quality, safety, efficiency, and interoperability across products, services, and systems.
  • D. BSI
    BSI is the Botanical Survey of India, the national organization responsible for surveying, researching, and documenting the plant resources of India.
  • E. BSI
    BSI is the vehicle registration code used on license plates for cars registered in Siemiatycze, Poland.
  • 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_69d8dd025c188190a1d81f5b4ec7e2c6 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d6ddc9608190a1daec9ddcc79a7a completed April 20, 2026, 7:33 a.m.
Created at: April 10, 2026, 12:02 p.m.