Triple

T10784796
Position Surface form Disambiguated ID Type / Status
Subject The Flaying of Marsyas E254424 entity
Predicate city P40 FINISHED
Object Kroměříž E448060 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: Kroměříž | Statement: [The Flaying of Marsyas, city, Kroměříž]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kroměříž
Context triple: [The Flaying of Marsyas, city, Kroměříž]
  • A. Kroměříž chosen
    Kroměříž is a historic town in the Czech Republic known for its UNESCO-listed Archbishop’s Chateau and Baroque gardens.
  • B. Kolín
    Kolín is a historic industrial town and important transport hub on the Elbe River in the Central Bohemian Region of the Czech Republic.
  • C. Havlíčkův Brod
    Havlíčkův Brod is a historic town in the Vysočina Region of the Czech Republic, situated on the Sázava River and known for its medieval center and long-standing brewing tradition.
  • D. Hradec Králové
    Hradec Králové is a historic city in the Czech Republic known for its educational institutions, modernist architecture, and role as a regional cultural and economic center.
  • E. Olomouc
    Olomouc is a historic city in the eastern Czech Republic known for its well-preserved old town, Baroque architecture, and UNESCO-listed Holy Trinity Column.
  • 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_69d6aa609f008190a294200aefcb7bd5 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d732d2e7cc8190a4cb9a4d7c76ab15 completed April 9, 2026, 5:02 a.m.
NED1 Entity disambiguation (via context triple) batch_69f6684574908190bd7e3d1a7dd6d876 completed May 2, 2026, 9:10 p.m.
Created at: April 8, 2026, 9:17 p.m.