Triple

T23553488
Position Surface form Disambiguated ID Type / Status
Subject Potsdam Hbf E578116 entity
Predicate connectsTo P845 FINISHED
Object Berlin Wannsee 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: Berlin Wannsee | Statement: [Potsdam Hbf, connectsTo, Berlin Wannsee]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Berlin Wannsee
Context triple: [Potsdam Hbf, connectsTo, Berlin Wannsee]
  • A. Wannsee chosen
    Wannsee is a lakeside district in southwestern Berlin, Germany, known for its villa colonies, recreational waterfront, and as the site of the infamous 1942 Wannsee Conference.
  • B. Spandau
    Spandau is a western borough of Berlin, Germany, known for its historic old town, fortress, and role as an important residential and industrial district.
  • C. Sachsenhausen
    Sachsenhausen is a historic and culturally vibrant district of Frankfurt am Main, known for its traditional apple wine taverns, museums, and picturesque old town streets.
  • D. Sachsenhausen
    Sachsenhausen is a district or neighborhood within the town of Giengen an der Brenz in the German state of Baden-Württemberg.
  • E. Seelow
    Seelow is a small town in eastern Brandenburg, Germany, best known today as the administrative center of the Märkisch-Oderland district and for its proximity to the historic Seelow Heights battlefield of World War II.
  • 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_69e245fa93448190919cb04534560542 completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f1aed17fc881908b45dcde14790d42 completed April 29, 2026, 7:10 a.m.
Created at: April 17, 2026, 6:11 p.m.