Triple

T17836401
Position Surface form Disambiguated ID Type / Status
Subject Max Berg E445398 entity
Predicate name P16 FINISHED
Object Max Berg 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: Max Berg | Statement: [Max Berg, name, Max Berg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Max Berg
Context triple: [Max Berg, name, Max Berg]
  • A. Max Berg chosen
    Max Berg was a German architect best known for his pioneering expressionist and reinforced-concrete designs in the early 20th century.
  • B. Oskar Hagen
    Oskar Hagen was a German art historian and musicologist best known for reviving interest in George Frideric Handel’s operas and helping to establish modern Handel performance traditions.
  • C. Albert Paulsen
    Albert Paulsen was an Ecuadorian-American character actor known for his frequent villainous roles in American film and television during the 1960s and 1970s.
  • D. Ferdinand Boberg
    Ferdinand Boberg was a prominent Swedish architect of the late 19th and early 20th centuries, known for his influential contributions to national romantic and Art Nouveau architecture in Sweden.
  • E. Rolf Bruhn
    Rolf Bruhn was a Canadian politician and businessman who served as a member of the Legislative Assembly of British Columbia in the early 20th century.
  • 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_69d8b9f1a6d881909f024bc603111cdb completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e48d27f8908190bf48a8153756effa completed April 19, 2026, 8:07 a.m.
Created at: April 10, 2026, 10:16 a.m.