Triple

T20352115
Position Surface form Disambiguated ID Type / Status
Subject Michael Kremer E496037 entity
Predicate familyName P18 FINISHED
Object Kremer 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: Kremer | Statement: [Michael Kremer, familyName, Kremer]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kremer
Context triple: [Michael Kremer, familyName, Kremer]
  • A. Kremer chosen
    Kremer is the surname of Gidon Kremer, a renowned Latvian-born violinist and conductor known for his interpretations of both classical and contemporary repertoire.
  • B. Cremer
    Cremer is a surname most notably associated with William Randal Cremer, a British politician and Nobel Peace Prize laureate recognized for his work in international arbitration.
  • C. Kretzmer
    Kretzmer is a surname most notably associated with Herbert Kretzmer, the South African-born British journalist and lyricist known for his work on the musical Les Misérables.
  • D. Krenkel
    Krenkel is a German-language surname most notably associated with the polar explorer Ernst Krenkel.
  • E. de Kremer
    de Kremer is the original family surname of the renowned 16th-century Flemish cartographer Gerardus Mercator.
  • 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_69e0b4a3f7f48190b37f354574028ca6 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e67850ace48190b19aff5780fef7e8 completed April 20, 2026, 7:02 p.m.
Created at: April 16, 2026, 11:25 a.m.