Triple

T20205764
Position Surface form Disambiguated ID Type / Status
Subject Marina Rodnina E493344 entity
Predicate hasWorkplace P1527 FINISHED
Object Göttingen 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: Göttingen | Statement: [Marina Rodnina, hasWorkplace, Göttingen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Göttingen
Context triple: [Marina Rodnina, hasWorkplace, Göttingen]
  • A. Göttingen chosen
    Göttingen is a historic university city in Lower Saxony, Germany, renowned for its prestigious Georg-August University and contributions to science and mathematics.
  • B. Heidberg
    Heidberg is a small locality or district that forms part of the town of Rüthen in North Rhine-Westphalia, Germany.
  • C. Darmstadt
    Darmstadt is a city in the German state of Hesse known for its historical ties to the Grand Duchy of Hesse and its role as a center of science, technology, and Art Nouveau culture.
  • D. Greifswald
    Greifswald is a historic Hanseatic university city in northeastern Germany, located near the Baltic Sea.
  • E. Heidelberg
    Heidelberg is a suburb of Melbourne, Australia, known for its historic role in Australian Impressionism and its location along the Yarra River.
  • 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_69da6269614c8190bb40475d9d477358 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e66d913c088190b80b251fba5c368f completed April 20, 2026, 6:16 p.m.
Created at: April 11, 2026, 11:38 p.m.