Triple

T21196051
Position Surface form Disambiguated ID Type / Status
Subject HMS Suffolk E522328 entity
Predicate class P87 FINISHED
Object County class 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: County class | Statement: [HMS Suffolk, class, County class]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: County class
Context triple: [HMS Suffolk, class, County class]
  • A. County class chosen
    The County class was a group of British Royal Navy heavy cruisers built under the constraints of the interwar naval treaties and serving prominently during the Second World War.
  • B. Y class
    Y class is the standard economy fare class used by airlines, typically representing full-fare economy tickets with the least restrictions on changes and refunds.
  • C. Classe
    Classe is a historic coastal area near Ravenna in Italy, renowned for its early Christian monuments and archaeological remains.
  • D. Class B
    Class B is a type of controlled airspace surrounding the busiest airports, designed to manage high volumes of air traffic with strict clearance and communication requirements.
  • E. National Unit
    The National Unit is a specialized division of the Dutch police responsible for nationwide and international operations, complex investigations, and support to regional police forces.
  • 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_69e0b51061388190aa03f19700d3ef04 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e7333bd7a0819084bbd1d6c111bc65 completed April 21, 2026, 8:20 a.m.
Created at: April 16, 2026, 3:08 p.m.