Triple

T10452355
Position Surface form Disambiguated ID Type / Status
Subject Sevnica E246457 entity
Predicate hasLandmark P105 FINISHED
Object Sevnica Castle E863403 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: Sevnica Castle | Statement: [Sevnica, hasLandmark, Sevnica Castle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sevnica Castle
Context triple: [Sevnica, hasLandmark, Sevnica Castle]
  • A. Sevnica Castle chosen
    Sevnica Castle is a medieval hilltop fortress in Sevnica, Slovenia, known for its well-preserved architecture and panoramic views over the Sava River valley.
  • B. Ptuj Castle
    Ptuj Castle is a medieval hilltop fortress in the Slovenian town of Ptuj, now serving as a museum and prominent cultural landmark overlooking the Drava River.
  • C. Likava Castle
    Likava Castle is a medieval ruin in northern Slovakia, historically significant as a former royal and defensive stronghold overlooking key trade routes.
  • D. Ljubljana Castle
    Ljubljana Castle is a medieval hilltop fortress overlooking Slovenia’s capital, now a major cultural venue and tourist attraction with panoramic views of Ljubljana.
  • E. Gorizia Castle
    Gorizia Castle is a medieval fortress in the Italian town of Gorizia, notable for its hilltop position, well-preserved defensive structures, and role in the region’s historical conflicts.
  • 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_69d381c04fe08190957c26c526a3b05a completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4fe0b7bb481908182c7b9a80af3b3 completed April 7, 2026, 12:52 p.m.
NED1 Entity disambiguation (via context triple) batch_69d89fb27f5081909e78bd8029e65948 completed April 10, 2026, 6:58 a.m.
Created at: April 6, 2026, 12:17 p.m.