Triple

T10531940
Position Surface form Disambiguated ID Type / Status
Subject Katherina Mann E248463 entity
Predicate givenName P17 FINISHED
Object Katherina E248463 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: Katherina | Statement: [Katherina Mann, givenName, Katherina]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Katherina
Context triple: [Katherina Mann, givenName, Katherina]
  • A. Katherina chosen
    Katherina is the given first name of Katia Mann, the wife of German novelist Thomas Mann.
  • B. Katherina
    Katherina is the sharp-tongued, strong-willed heroine of Shakespeare’s comedy *The Taming of the Shrew*, whose fiery personality and contentious courtship drive the play’s central conflict.
  • C. Katharina
    Katharina is a feminine given name, commonly used in German-speaking and other European countries, that is a variant of Katherine/Catherine.
  • D. Julietta
    Julietta is a surreal three-act opera by Czech composer Bohuslav Martinů, based on Georges Neveux’s play about a man searching for a woman in a dreamlike town where people have lost their memories.
  • E. Beatrice
    Beatrice is the idealized woman in Dante Alighieri’s Divine Comedy who serves as his spiritual guide through Paradise and symbolizes divine love and theology.
  • 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_69d381c5c7448190bec34bee7ec72bac completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d50a17f23081909f3372e160e21670 completed April 7, 2026, 1:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69d90e471e9c8190b134249073b289bd completed April 10, 2026, 2:50 p.m.
Created at: April 6, 2026, 12:30 p.m.