Triple

T7732122
Position Surface form Disambiguated ID Type / Status
Subject Soest E175283 entity
Predicate locatedWestOf P4239 FINISHED
Object Paderborn E315002 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: Paderborn | Statement: [Soest, locatedWestOf, Paderborn]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Paderborn
Context triple: [Soest, locatedWestOf, Paderborn]
  • A. Paderborn chosen
    Paderborn is a historic city in western Germany known for its medieval cathedral, role as a regional religious and cultural center, and strategic importance during World War II.
  • B. Osnabrück
    Osnabrück is a historic city in Lower Saxony, Germany, known for its medieval architecture and role in the Peace of Westphalia.
  • C. Bielefeld
    Bielefeld is a major city in northwestern Germany known for its industrial heritage, university, and the tongue-in-cheek “Bielefeld conspiracy” meme claiming it does not exist.
  • D. Lippstadt
    Lippstadt is a historic town in North Rhine-Westphalia, Germany, known for its medieval architecture and role in regional conflicts.
  • E. Münster
    Münster is a historic city in western Germany known as one of the principal sites where the Peace of Westphalia treaties were negotiated and signed, ending the Thirty Years' War in 1648.
  • 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_69c6995e912c81909a49a2657103f786 completed March 27, 2026, 2:51 p.m.
NER Named-entity recognition batch_69c70336aafc819099a060950ab8922f completed March 27, 2026, 10:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69d02f04ab008190a4c98a8f00ec4c20 completed April 3, 2026, 9:20 p.m.
Created at: March 27, 2026, 4:06 p.m.