Triple

T12796304
Position Surface form Disambiguated ID Type / Status
Subject Italian cruiser Pola E305898 entity
Predicate class P87 FINISHED
Object Zara class E365954 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: Zara class | Statement: [Italian cruiser Pola, class, Zara class]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Zara class
Context triple: [Italian cruiser Pola, class, Zara class]
  • A. Zara-class cruisers chosen
    The Zara-class cruisers were a group of Italian heavy cruisers of the Regia Marina, noted for their heavy armor and participation in key World War II Mediterranean naval battles.
  • B. Dido class
    The Dido class was a group of British Royal Navy light anti-aircraft cruisers built and used during World War II.
  • C. Royal Laurel Class
    Royal Laurel Class is EVA Air's premium long-haul business class product, featuring lie-flat seats, enhanced privacy, and upgraded dining and service.
  • D. Type 42 destroyer
    The Type 42 destroyer was a class of Royal Navy guided-missile destroyers designed primarily for anti-air warfare, notably serving in front-line roles during the late Cold War era.
  • E. Type 45 destroyers
    Type 45 destroyers are advanced British Royal Navy air-defence warships designed primarily to protect fleets from aerial and missile threats using sophisticated radar and missile systems.
  • 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_69d7bdf366888190a8cccb982606889c completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d96e6db68481909a2ca8da1287f3e0 completed April 10, 2026, 9:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69f68ec0d5dc819099a8036c6cbac634 completed May 2, 2026, 11:54 p.m.
Created at: April 9, 2026, 5:30 p.m.