Triple

T18294208
Position Surface form Disambiguated ID Type / Status
Subject Nice Classification E438189 entity
Predicate abbreviation P43 FINISHED
Object NCL 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: NCL | Statement: [Nice Classification, abbreviation, NCL]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: NCL
Context triple: [Nice Classification, abbreviation, NCL]
  • A. NCL chosen
    NCL is the commonly used abbreviation for the Nice Classification, an international system for categorizing goods and services for trademark registration.
  • B. NCL
    NCL is the three-letter National Rail station code for Newcastle railway station, a major rail hub in Newcastle upon Tyne, England.
  • C. NCL
    NCL is the IATA airport code for Newcastle International Airport, a major airport serving Newcastle upon Tyne and the surrounding region in northeast England.
  • D. NetCDF
    NetCDF is a widely used, self-describing, machine-independent data format and set of software libraries designed for storing and sharing array-oriented scientific data, especially in the geosciences.
  • E. IBM ESSL
    IBM ESSL (Engineering and Scientific Subroutine Library) is IBM’s optimized mathematical library providing high-performance routines for numerical linear algebra and related scientific computing tasks on IBM systems.
  • 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_69d8b915e3e881909125d760c15d0c29 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e5010205bc8190a32fe731ead3d988 completed April 19, 2026, 4:21 p.m.
Created at: April 10, 2026, 10:35 a.m.