Triple

T17697078
Position Surface form Disambiguated ID Type / Status
Subject Rock Riding School E441198 entity
Predicate carvedInto P40987 FINISHED
Object Mönchsberg rock 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: Mönchsberg rock | Statement: [Rock Riding School, carvedInto, Mönchsberg rock]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mönchsberg rock
Context triple: [Rock Riding School, carvedInto, Mönchsberg rock]
  • A. Mönchsberg chosen
    Mönchsberg is a prominent wooded hill in the center of Salzburg, Austria, known for its scenic walking paths, historic fortifications, and panoramic views over the old town.
  • B. Brocke
    Brocke is a variant form of the given name Brock, typically used as a masculine first name.
  • C. Witzmannsberg
    Witzmannsberg is a small rural municipality in the Bavarian region of Lower Bavaria, Germany, known for its scenic countryside and traditional village character.
  • D. Pfingstberg hill
    Pfingstberg hill is a prominent elevation in Potsdam, Germany, known for its scenic views and historic landscape architecture, including royal gardens and palatial structures.
  • E. Michaelsberg hill
    Michaelsberg hill is a prominent elevation in Siegburg, Germany, known for its historic monastery and panoramic views over the surrounding region.
  • 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_69d8b9ea20b48190ace88bb46b01e6a9 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e47157fd688190ba990eaf46ceab01 completed April 19, 2026, 6:08 a.m.
Created at: April 10, 2026, 10:04 a.m.