Triple

T9470405
Position Surface form Disambiguated ID Type / Status
Subject Deutsches Filmmuseum E228374 entity
Predicate cityDistrict P2709 FINISHED
Object Sachsenhausen E131173 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: Sachsenhausen | Statement: [Deutsches Filmmuseum, cityDistrict, Sachsenhausen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sachsenhausen
Context triple: [Deutsches Filmmuseum, cityDistrict, Sachsenhausen]
  • A. Sachsenhausen
    Sachsenhausen is a district or neighborhood within the town of Giengen an der Brenz in the German state of Baden-Württemberg.
  • B. Sachsenhausen chosen
    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.
  • C. 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.
  • D. Neu-Hohenschönhausen
    Neu-Hohenschönhausen is a residential locality in the northeast of Berlin, known for its large prefabricated housing estates and post-war urban development.
  • E. Ludwigsfelde
    Ludwigsfelde is a town in the German state of Brandenburg, located just south of Berlin and known for its industrial history and automotive manufacturing.
  • 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_69ca847162c48190b079076c9595513c completed March 30, 2026, 2:10 p.m.
NER Named-entity recognition batch_69cd7fee13a88190b4532fb92ddaf401 completed April 1, 2026, 8:28 p.m.
NED1 Entity disambiguation (via context triple) batch_69d122c45ae88190a43d70300bed98da completed April 4, 2026, 2:40 p.m.
Created at: March 30, 2026, 7:53 p.m.