Triple

T16690159
Position Surface form Disambiguated ID Type / Status
Subject Leonor Ernestina von Daun E405572 entity
Predicate familyName P18 FINISHED
Object von Daun E1148951 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: von Daun | Statement: [Leonor Ernestina von Daun, familyName, von Daun]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: von Daun
Context triple: [Leonor Ernestina von Daun, familyName, von Daun]
  • A. von Daun chosen
    Von Daun is a German noble surname most notably associated with an Austrian military family prominent in the 18th century.
  • B. von Bock
    Von Bock is a German noble surname most prominently associated with Fedor von Bock, a senior Wehrmacht field marshal during World War II.
  • C. Dauch
    Dauch is a surname of French origin borne by individuals such as Martin-Dauch.
  • D. von Münnich
    von Münnich is the noble German family name of Burkhard Christoph von Münnich, an 18th-century military commander and statesman who served in the Russian Empire.
  • E. von Falkenhausen
    Von Falkenhausen is a German noble family name historically associated with military and administrative figures in Prussia and the German Empire.
  • 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_69d8838c28748190b3f5967c743940ab completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e37ea8cabc8190ba321503399960da completed April 18, 2026, 12:52 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0091966fbc81908cd1db230ddbb82b completed May 10, 2026, 2:09 p.m.
Created at: April 10, 2026, 5:19 a.m.