Triple

T13097686
Position Surface form Disambiguated ID Type / Status
Subject Andreas Karlstadt E310632 entity
Predicate workLocation P7 FINISHED
Object Orlamünde E693405 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: Orlamünde | Statement: [Andreas Karlstadt, workLocation, Orlamünde]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Orlamünde
Context triple: [Andreas Karlstadt, workLocation, Orlamünde]
  • A. Orlamünde chosen
    Orlamünde is a small historic town in the German state of Thuringia, situated along the Saale River.
  • B. Orlem
    Orlem is a prominent residential neighborhood in the Malad suburb of Mumbai, known for its churches, schools, and bustling local markets.
  • C. Vendryně
    Vendryně is a village in the Moravian-Silesian Region of the Czech Republic, known for its location in the historical region of Cieszyn Silesia near the Olza River.
  • D. Flerzheim
    Flerzheim is a village and district of the town of Rheinbach in the Rhein-Sieg-Kreis region of North Rhine-Westphalia, Germany.
  • E. Ländtor
    Ländtor is a historic city gate in Landshut, Germany, known as one of the town’s most prominent medieval landmarks.
  • 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_69d806a733548190989cfd4ce981ca33 completed April 9, 2026, 8:05 p.m.
NER Named-entity recognition batch_69d9814e88a0819088418c792ce7aa57 completed April 10, 2026, 11:01 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6d619b82c819093d0d98db88eb9ae completed May 3, 2026, 4:59 a.m.
Created at: April 9, 2026, 9:04 p.m.