Triple

T22591257
Position Surface form Disambiguated ID Type / Status
Subject Steiff Museum E564953 entity
Predicate exhibits P4908 FINISHED
Object Steiff company archives 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: Steiff company archives | Statement: [Steiff Museum, exhibits, Steiff company archives]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Steiff company archives
Context triple: [Steiff Museum, exhibits, Steiff company archives]
  • A. Steiff Museum chosen
    The Steiff Museum is a German museum dedicated to the history, craftsmanship, and iconic teddy bears and plush toys of the Steiff company.
  • B. Margarete Steiff GmbH
    Margarete Steiff GmbH is a German toy company famous worldwide for inventing the modern teddy bear and producing high-quality plush animals.
  • C. Ertl Company
    Ertl Company is an American manufacturer best known for producing die-cast metal toy replicas of farm equipment, vehicles, and other collectibles.
  • D. Deutsches Ledermuseum
    Deutsches Ledermuseum is a German museum renowned for its extensive collections on the history, craft, and cultural significance of leather and leather goods.
  • E. Ertl
    Ertl is a German surname most notably associated with Nobel Prize–winning physicist and surface chemist Gerhard Ertl.
  • 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_69e245836014819091b91ed3074742a3 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f16160651081909d23735336fd7a16 completed April 29, 2026, 1:39 a.m.
Created at: April 17, 2026, 2:48 p.m.