Triple

T15255616
Position Surface form Disambiguated ID Type / Status
Subject SMS Kronprinz Wilhelm E364638 entity
Predicate sisterShipOf P3142 FINISHED
Object SMS König E236956 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: SMS König | Statement: [SMS Kronprinz Wilhelm, sisterShipOf, SMS König]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: SMS König
Context triple: [SMS Kronprinz Wilhelm, sisterShipOf, SMS König]
  • A. SMS König chosen
    SMS König was a German Kaiser-class battleship that served as the lead ship of her class in the Imperial German Navy during World War I, notably participating in the Battle of Jutland.
  • B. SMS König Wilhelm
    SMS König Wilhelm was a 19th-century Prussian ironclad warship that served as a powerful armored frigate and later as a flagship in the Imperial German Navy.
  • C. SMS Kronprinz
    SMS Kronprinz was a German Kaiserliche Marine König-class battleship that served in World War I, including at the Battle of Jutland.
  • D. SMS Saida
    SMS Saida was a light cruiser of the Austro-Hungarian Navy that served during World War I in the Adriatic Sea.
  • E. SMS Arminius
    SMS Arminius was a 19th-century Prussian ironclad warship that played a key role in the early development of Germany’s armored naval forces.
  • 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_69d85a0dde7481908fc64d1e82d5d20d completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e0084b97908190b3bf7ea7bd75bdc0 completed April 15, 2026, 9:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69fee5f7bd2081909c003deb3a692f18 completed May 9, 2026, 7:44 a.m.
Created at: April 10, 2026, 3:13 a.m.