Triple

T16848406
Position Surface form Disambiguated ID Type / Status
Subject anti-king of Germany E409604 entity
Predicate GermanName P6492 FINISHED
Object Gegenkönig
Gegenkönig is the German term for a rival or counter-king who claims the throne in opposition to a reigning monarch, especially in the context of medieval German history.
E1236206 NE FINISHED

How this triple was built (4 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: Gegenkönig | Statement: [anti-king of Germany, GermanName, Gegenkönig]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gegenkönig
Context triple: [anti-king of Germany, GermanName, Gegenkönig]
  • A. König
    König is a German-language surname borne by numerous individuals, including notable figures in fields such as religion, science, and the arts.
  • B. Kœnig
    Kœnig is a French surname most notably associated with figures such as General Marie-Pierre Kœnig, a prominent military leader during World War II.
  • C. Prince of Liège
    Prince of Liège was the courtesy title held by Albert II of Belgium before he ascended the throne as King of the Belgians.
  • D. Herzog von Berg
    Herzog von Berg is the German title historically used for the dukes who ruled the Duchy of Berg in the Holy Roman Empire.
  • E. Koning
    Koning is a Dutch surname and term meaning “king,” commonly used in the Netherlands and Belgium.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Gegenkönig
Triple: [anti-king of Germany, GermanName, Gegenkönig]
Generated description
Gegenkönig is the German term for a rival or counter-king who claims the throne in opposition to a reigning monarch, especially in the context of medieval German history.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Gegenkönig
Target entity description: Gegenkönig is the German term for a rival or counter-king who claims the throne in opposition to a reigning monarch, especially in the context of medieval German history.
  • A. König
    König is a German-language surname borne by numerous individuals, including notable figures in fields such as religion, science, and the arts.
  • B. Kœnig
    Kœnig is a French surname most notably associated with figures such as General Marie-Pierre Kœnig, a prominent military leader during World War II.
  • C. Prince of Liège
    Prince of Liège was the courtesy title held by Albert II of Belgium before he ascended the throne as King of the Belgians.
  • D. Herzog von Berg
    Herzog von Berg is the German title historically used for the dukes who ruled the Duchy of Berg in the Holy Roman Empire.
  • E. Koning
    Koning is a Dutch surname and term meaning “king,” commonly used in the Netherlands and Belgium.
  • F. None of above. chosen

Provenance (5 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_69d883952b048190887740a980b712ed completed April 10, 2026, 4:59 a.m.
NER Named-entity recognition batch_69e3b376bac48190ae09f29a28c55f8c completed April 18, 2026, 4:38 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00bb1d555c8190883c82e562b7bfe9 completed May 10, 2026, 5:06 p.m.
NEDg Description generation batch_6a00bbb628208190b0be62a333e7e442 completed May 10, 2026, 5:09 p.m.
NED2 Entity disambiguation (via description) batch_6a00bc3a4b888190bd190b9330e2777d completed May 10, 2026, 5:11 p.m.
Created at: April 10, 2026, 5:24 a.m.