Triple

T13485659
Position Surface form Disambiguated ID Type / Status
Subject Erhard E318493 entity
Predicate hasVariant P455 FINISHED
Object Erhardt
Erhardt is a German surname and given name, often considered a variant of Erhard, and is borne by various notable individuals in fields such as sports, arts, and public life.
 E1042081 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: Erhardt | Statement: [Erhard, hasVariant, Erhardt]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Erhardt
Context triple: [Erhard, hasVariant, Erhardt]
  • A. Reubell
    Reubell is a French surname most notably associated with Jean-François Reubell, a prominent political figure during the French Revolution and a member of the Directory.
  • B. Oberhauser
    Oberhauser is a German-language surname borne by various notable individuals across fields such as sports, the arts, and public life.
  • C. Hartmann
    Hartmann is a German surname borne by numerous notable individuals across fields such as music, philosophy, and aviation.
  • D. Habermann
    Habermann is a 2010 Czech-German war drama film directed by Juraj Herz that portrays the moral and ethnic tensions in a Sudeten village during and after World War II.
  • E. Günther
    Günther is the zoologist who first formally described the impressed tortoise species Manouria impressa.
  • 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: Erhardt
Triple: [Erhard, hasVariant, Erhardt]
Generated description
Erhardt is a German surname and given name, often considered a variant of Erhard, and is borne by various notable individuals in fields such as sports, arts, and public life.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Erhardt
Target entity description: Erhardt is a German surname and given name, often considered a variant of Erhard, and is borne by various notable individuals in fields such as sports, arts, and public life.
  • A. Reubell
    Reubell is a French surname most notably associated with Jean-François Reubell, a prominent political figure during the French Revolution and a member of the Directory.
  • B. Oberhauser
    Oberhauser is a German-language surname borne by various notable individuals across fields such as sports, the arts, and public life.
  • C. Hartmann
    Hartmann is a German surname borne by numerous notable individuals across fields such as music, philosophy, and aviation.
  • D. Habermann
    Habermann is a 2010 Czech-German war drama film directed by Juraj Herz that portrays the moral and ethnic tensions in a Sudeten village during and after World War II.
  • E. Günther
    Günther is the zoologist who first formally described the impressed tortoise species Manouria impressa.
  • 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_69d806b6bfec819089222715b2e86c8e completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69dbaf3a15b48190b63fb59e926a97ae completed April 12, 2026, 2:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69f7463715dc8190a70a17b3ea661006 completed May 3, 2026, 12:57 p.m.
NEDg Description generation batch_69f74bac36e081909dae786e14883e3c completed May 3, 2026, 1:20 p.m.
NED2 Entity disambiguation (via description) batch_69f74c5195188190bad111b301713426 completed May 3, 2026, 1:23 p.m.
Created at: April 9, 2026, 9:42 p.m.