Triple

T19019621
Position Surface form Disambiguated ID Type / Status
Subject International Standard Industrial Classification E465447 entity
Predicate latestVersion P3698 FINISHED
Object ISIC Rev.4 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: ISIC Rev.4 | Statement: [International Standard Industrial Classification, latestVersion, ISIC Rev.4]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ISIC Rev.4
Context triple: [International Standard Industrial Classification, latestVersion, ISIC Rev.4]
  • A. ISIC chosen
    ISIC is the internationally recognized system for classifying economic activities used for statistics, economic analysis, and policy-making.
  • B. Skinfaxi
    Skinfaxi is the shining horse of Norse mythology that pulls the day across the sky for the deity Dagr.
  • C. MDSD
    MDSD is the ICAO airport code for Las Américas International Airport, a major international gateway serving Santo Domingo in the Dominican Republic.
  • D. MRSD
    MRSD is a specialized graduate program focused on the practical design, development, and deployment of advanced robotic systems.
  • E. MRSD
    MRSD is the commonly used abbreviation for the Molalla River School District, a public school district serving the Molalla area in Oregon.
  • 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.