Triple

T10988204
Position Surface form Disambiguated ID Type / Status
Subject Main-Spessart E259685 entity
Predicate capital P234 FINISHED
Object Karlstadt E832497 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: Karlstadt | Statement: [Main-Spessart, capital, Karlstadt]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Karlstadt
Context triple: [Main-Spessart, capital, Karlstadt]
  • A. Karlstadt am Main chosen
    Karlstadt am Main is a historic town in northern Bavaria, Germany, situated on the River Main and known for its medieval old town and surrounding wine-growing region.
  • B. Wittenberge
    Wittenberge is a small town in the state of Brandenburg in northeastern Germany, situated on the Elbe River and known for its historic industrial architecture and riverside setting.
  • C. Wittenberg
    Wittenberg is a historic German city best known as the cradle of the Protestant Reformation and the place where Martin Luther taught and preached.
  • D. Village of Wittenberg
    The Village of Wittenberg is a small rural community in central Wisconsin known for its agricultural surroundings and local small-town character.
  • E. Arnstadt
    Arnstadt is a historic town in Thuringia, Germany, known for its early associations with the Bach family and its well-preserved medieval architecture.
  • 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_69d6aa8a6a548190a750f944ccdc8064 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d787b574d08190adec34b814a26437 completed April 9, 2026, 11:04 a.m.
NED1 Entity disambiguation (via context triple) batch_69e374639f1481908ea372b81a834f6f completed April 18, 2026, 12:09 p.m.
Created at: April 8, 2026, 9:24 p.m.