Triple

T22605274
Position Surface form Disambiguated ID Type / Status
Subject Riksmarsk E566538 entity
Predicate hasAlternativeName P39 FINISHED
Object Marsk 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: Marsk | Statement: [Riksmarsk, hasAlternativeName, Marsk]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marsk
Context triple: [Riksmarsk, hasAlternativeName, Marsk]
  • A. Schleye
    Schleye is a variant spelling of the surname Schley, which is of German origin.
  • B. Riksmarsk chosen
    Riksmarsk was the historical title for Sweden’s highest military commander and one of the great officers of the realm.
  • C. Reventlow
    Reventlow is the noble Danish family name historically associated with figures such as Queen consort Anna Sophie Reventlow.
  • D. Scaër
    Scaër is a commune in the Finistère department of Brittany in northwestern France, known for its rural landscapes and location within the canton of Moëlan-sur-Mer.
  • E. Lisberg
    Lisberg is a Danish-origin surname most notably associated with figures such as Jens Oliver Lisberg.
  • 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_69e245884860819081046ce07d5872c4 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f162709d808190af83837104a190f9 completed April 29, 2026, 1:44 a.m.
Created at: April 17, 2026, 2:53 p.m.