Triple

T20461242
Position Surface form Disambiguated ID Type / Status
Subject Christian Sebaldt E501927 entity
Predicate name P16 FINISHED
Object Christian Sebaldt 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: Christian Sebaldt | Statement: [Christian Sebaldt, name, Christian Sebaldt]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Christian Sebaldt
Context triple: [Christian Sebaldt, name, Christian Sebaldt]
  • A. Christian Sebaldt chosen
    Christian Sebaldt is a German-born cinematographer known for his work on genre films and television series, including the action-horror movie "Resident Evil: Apocalypse."
  • B. Arvid Wittenberg
    Arvid Wittenberg was a 17th-century Swedish field marshal and nobleman known for his prominent role in Sweden’s military campaigns during the Second Northern War.
  • C. Christoph Herborn
    Christoph Herborn is a German local politician who serves as the mayor of the town of Diez in Rhineland-Palatinate.
  • D. Johann von Thielmann
    Johann von Thielmann was a Prussian general of the Napoleonic Wars, noted for his leadership of Prussian forces during the Waterloo campaign.
  • E. Gotthard Heinrici
    Gotthard Heinrici was a German Wehrmacht field marshal renowned as one of Nazi Germany’s most skilled defensive commanders during World War II, particularly in the war’s final stages.
  • 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_69e0b4ad4940819098cf2ff6413574e5 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e696a642648190808709020f91122b completed April 20, 2026, 9:12 p.m.
Created at: April 16, 2026, 11:33 a.m.