Triple

T20203658
Position Surface form Disambiguated ID Type / Status
Subject Lothar Rendulic E493289 entity
Predicate givenName P17 FINISHED
Object Lothar 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: Lothar | Statement: [Lothar Rendulic, givenName, Lothar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lothar
Context triple: [Lothar Rendulic, givenName, Lothar]
  • A. Lothar chosen
    Lothar is a masculine given name of Germanic origin, historically borne by various European nobles, military figures, and notable individuals.
  • B. Lothar König
    Lothar König was a German Jesuit priest and member of the anti-Nazi resistance group associated with the Kreisau Circle during World War II.
  • C. Lothar the Lame
    Lothar the Lame was a lesser-known Frankish prince of the 9th century, notable mainly as a physically disabled son of the West Frankish king and Holy Roman Emperor Charles the Bald.
  • D. Gerhard
    Gerhard is a masculine given name of German origin, historically common in German-speaking countries.
  • E. Eberhard
    Eberhard is a German masculine given name of Old High German origin, traditionally meaning "strong boar" or "brave boar."
  • 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_69da6269614c8190bb40475d9d477358 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e66d8f90108190b72e37c0056de0f8 completed April 20, 2026, 6:16 p.m.
Created at: April 11, 2026, 11:38 p.m.