Triple

T20995750
Position Surface form Disambiguated ID Type / Status
Subject Bavaria Studios E517143 entity
Predicate locatedIn P40 FINISHED
Object Geiselgasteig 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: Geiselgasteig | Statement: [Bavaria Studios, locatedIn, Geiselgasteig]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Geiselgasteig
Context triple: [Bavaria Studios, locatedIn, Geiselgasteig]
  • A. Geiselgasteig chosen
    Geiselgasteig is a district in the southern part of Munich, Germany, best known as a major center of film and television production.
  • B. Neutraubling
    Neutraubling is a town in Bavaria, Germany, located near the city of Regensburg and known for its post-World War II development and industrial presence.
  • C. Leutkirch im Allgäu
    Leutkirch im Allgäu is a historic town in the Allgäu region of southern Germany, known for its medieval old town and scenic Alpine foothill surroundings.
  • D. Neusäß
    Neusäß is a town in Bavaria, Germany, located just northwest of the city of Augsburg and functioning largely as a residential and commuter suburb.
  • E. Geretsried
    Geretsried is a town in Upper Bavaria, Germany, situated on the Isar River and known as the largest town in the Bad Tölz-Wolfratshausen district.
  • 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_69e0b5006e2881909fc2383f841740cc completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e6fc1fd5d48190a56981cee95ebd69 completed April 21, 2026, 4:25 a.m.
Created at: April 16, 2026, 1:50 p.m.