Triple

T6954655
Position Surface form Disambiguated ID Type / Status
Subject Mark E161211 entity
Predicate hasVariant P455 FINISHED
Object Marek E352681 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: Marek | Statement: [Mark, hasVariant, Marek]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marek
Context triple: [Mark, hasVariant, Marek]
  • A. Marek chosen
    Marek is a common given name in several Slavic countries, equivalent to the Latin name Marcus.
  • B. Marek Belka
    Marek Belka is a Polish economist and politician who served as Prime Minister of Poland and later as president of the National Bank of Poland.
  • C. Feliks
    Feliks is a given name, commonly used in Slavic and other European languages, that corresponds to the name Felix.
  • D. Jacek
    Jacek is a common Polish male given name, often associated with notable figures in Polish politics, arts, and academia.
  • E. Husák
    Husák is a Slovak surname most prominently associated with Gustáv Husák, the communist politician who served as president of Czechoslovakia during the normalization era.
  • 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_69c68852a9a0819097797e31d492e273 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6dace1a94819095311e4288f01784 completed March 27, 2026, 7:30 p.m.
NED1 Entity disambiguation (via context triple) batch_69c75883f6888190a75515be49e7879e completed March 28, 2026, 4:26 a.m.
Created at: March 27, 2026, 2:29 p.m.