Triple

T20864615
Position Surface form Disambiguated ID Type / Status
Subject České středohoří E513719 entity
Predicate contains P35 FINISHED
Object Porta Bohemica 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: Porta Bohemica | Statement: [České středohoří, contains, Porta Bohemica]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Porta Bohemica
Context triple: [České středohoří, contains, Porta Bohemica]
  • A. Prague Gate
    Prague Gate is a historic city gate in Český Brod, Czech Republic, preserved as a notable remnant of the town’s medieval fortifications.
  • B. Prague Gate
    Prague Gate is a historic city gate in Žatec, Czech Republic, that once formed part of the town’s medieval fortifications.
  • C. Plzeňská Gate
    Plzeňská Gate is a historic city gate in Beroun, Czech Republic, notable as one of the town’s preserved medieval fortification structures.
  • D. Žatec Gate
    Žatec Gate is a historic city gate in Louny, Czech Republic, notable as a preserved remnant of the town’s medieval fortifications.
  • E. Moravian Gate chosen
    The Moravian Gate is a lowland corridor in the Czech Republic that forms a natural pass between the Sudetes and Carpathian Mountains, historically serving as an important route for transport and migration.
  • 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_69e0b4f5b01081909452f654d2fc3f50 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c45e51f08190ac1ff59280ad741b completed April 21, 2026, 12:27 a.m.
Created at: April 16, 2026, 12:44 p.m.