Triple

T14330656
Position Surface form Disambiguated ID Type / Status
Subject Nolde Museum Seebüll E355337 entity
Predicate locatedIn P40 FINISHED
Object Seebüll E1093863 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: Seebüll | Statement: [Nolde Museum Seebüll, locatedIn, Seebüll]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Seebüll
Context triple: [Nolde Museum Seebüll, locatedIn, Seebüll]
  • A. Seebüll chosen
    Seebüll is a small village in northern Germany best known as the longtime residence and studio of painter Emil Nolde, now home to a museum and foundation dedicated to his work.
  • B. Bokke
    Bokke is the popular nickname for South Africa’s national rugby union team, the Springboks.
  • C. Hecht
    Hecht is a surname of German and Jewish origin borne by various notable individuals across fields such as literature, politics, and science.
  • D. Bebra
    Bebra is a small settlement located in the historical region of Westphalia in western Germany.
  • E. Mümling
    The Mümling is a river in the Odenwald region of Germany that flows through Hesse and Bavaria before joining the Main.
  • 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_69d8278fa2108190bc0d0e7939c1eb03 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de8c1def0081908f03cda8e84d20c0 completed April 14, 2026, 6:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd4c3d20688190973e37ca38b4afe0 completed May 8, 2026, 2:36 a.m.
Created at: April 10, 2026, 1:13 a.m.