Triple

T2647992
Position Surface form Disambiguated ID Type / Status
Subject Brest E53827 entity
Predicate twinCity P1072 FINISHED
Object Kiel E108871 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: Kiel | Statement: [Brest, twinCity, Kiel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kiel
Context triple: [Brest, twinCity, Kiel]
  • A. Kiel chosen
    Kiel is a major port city in northern Germany on the Baltic Sea, known for its maritime industry and the annual Kiel Week sailing festival.
  • B. Frombork
    Frombork is a historic town in northern Poland best known as the place where astronomer Nicolaus Copernicus lived, worked, and was buried, and for its prominent cathedral complex overlooking the Vistula Lagoon.
  • C. Gdańsk
    Gdańsk is a major Polish port city on the Baltic Sea, known for its rich Hanseatic history, shipyards, and role in the origins of the Solidarity movement.
  • D. Königsberg
    Königsberg was a historic Prussian city on the Baltic Sea, renowned as a major cultural and intellectual center of East Prussia and later known as Kaliningrad.
  • E. Biebrich
    Biebrich is a district of Wiesbaden in the German state of Hesse, historically known as an independent town on the Rhine and the site of the Baroque Biebrich Palace.
  • 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_69ab495e192081909c77b622e8e7e15a completed March 6, 2026, 9:38 p.m.
NER Named-entity recognition batch_69abd91b4b3c81908571e85a1621dfc5 completed March 7, 2026, 7:51 a.m.
NED1 Entity disambiguation (via context triple) batch_69af98c944548190a8dbe9b81045e97b completed March 10, 2026, 4:06 a.m.
Created at: March 6, 2026, 9:53 p.m.