Triple

T20849511
Position Surface form Disambiguated ID Type / Status
Subject B 3 E513317 entity
Predicate connects P390 FINISHED
Object Offenburg 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: Offenburg | Statement: [B 3, connects, Offenburg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Offenburg
Context triple: [B 3, connects, Offenburg]
  • A. Offenburg chosen
    Offenburg is a city in southwestern Germany’s Baden-Württemberg state, known as a regional economic and transport hub near the French border in the Upper Rhine region.
  • B. Freudenstadt
    Freudenstadt is a spa and holiday town in southwestern Germany known for its large market square and location in the northern Black Forest.
  • C. Tuttlingen
    Tuttlingen is a town in the state of Baden-Württemberg in southern Germany, known as a major center of the medical technology and surgical instrument industry.
  • D. Ittlingen
    Ittlingen is a small municipality in the German state of Baden-Württemberg, located within the Heilbronn region.
  • E. Ebingen
    Ebingen is a district of Albstadt in the Swabian Jura region of Baden-Württemberg, Germany, historically known as an independent town and the birthplace of former German Chancellor Kurt Georg Kiesinger.
  • 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_69e0b4f4898081908209e58edb8f9c45 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c3520b0081908ce0f43e8f20b24c completed April 21, 2026, 12:22 a.m.
Created at: April 16, 2026, 12:43 p.m.