Triple

T6985731
Position Surface form Disambiguated ID Type / Status
Subject Herzog E161955 entity
Predicate hasNotableBearer P458 FINISHED
Object Roman Herzog E30668 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: Roman Herzog | Statement: [Herzog, hasNotableBearer, Roman Herzog]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Roman Herzog
Context triple: [Herzog, hasNotableBearer, Roman Herzog]
  • A. Roman Herzog chosen
    Roman Herzog was a German jurist and politician who served as President of Germany from 1994 to 1999.
  • B. Andreas von Weizsäcker
    Andreas von Weizsäcker was a German sculptor and member of the prominent von Weizsäcker family.
  • C. Siegfried Kohl
    Siegfried Kohl is an individual notable for bearing the German surname "Kohl," which is associated with several prominent figures.
  • D. Ernst von Weizsäcker
    Ernst von Weizsäcker was a German diplomat who served as State Secretary in the Foreign Office under the Nazi regime and was later convicted for his role in its policies at the post-World War II Ministries Trial.
  • E. Fritz von Weizsäcker
    Fritz von Weizsäcker was a German physician and professor of internal medicine who served as chief physician at Berlin’s Schlosspark-Klinik and was tragically killed during a public lecture in 2019.
  • 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_69c68855dc0481909b4c7e9e9ed273db completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6db93c0ac8190a752a633247bb439 completed March 27, 2026, 7:33 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7883f0d988190b170901aea57d360 completed March 28, 2026, 7:50 a.m.
Created at: March 27, 2026, 2:31 p.m.