Triple

T6827465
Position Surface form Disambiguated ID Type / Status
Subject My Century E157051 entity
Predicate publisher P29 FINISHED
Object Steidl Verlag E621538 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: Steidl Verlag | Statement: [My Century, publisher, Steidl Verlag]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Steidl Verlag
Context triple: [My Century, publisher, Steidl Verlag]
  • A. Steidl Verlag chosen
    Steidl Verlag is a renowned German publishing house best known for its high-quality art and photography books.
  • B. Kurt Wolff Verlag
    Kurt Wolff Verlag was an influential early 20th-century German publishing house known for championing modernist and expressionist literature, including works by authors such as Franz Kafka.
  • C. Insel Verlag
    Insel Verlag is a renowned German publishing house known for its influential literary catalog, including major works of modernist and classical literature.
  • D. Kiepenheuer Verlag
    Kiepenheuer Verlag is a German publishing house known for issuing significant 20th-century literary and dramatic works.
  • E. Gustav Fischer Verlag
    Gustav Fischer Verlag was a German academic publishing house known for producing influential works in economics, science, and the social sciences.
  • 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_69c6882a5b5c8190917a7db9ed36bad1 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d58583a4819099edbf753c7c7087 completed March 27, 2026, 7:07 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7426b3d2081909d0804a2fbc6efad completed March 28, 2026, 2:52 a.m.
Created at: March 27, 2026, 2:18 p.m.