Triple

T18764761
Position Surface form Disambiguated ID Type / Status
Subject Jakobshorn ski area E458863 entity
Predicate near P350 FINISHED
Object Davos Platz 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: Davos Platz | Statement: [Jakobshorn ski area, near, Davos Platz]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Davos Platz
Context triple: [Jakobshorn ski area, near, Davos Platz]
  • A. Davos Platz chosen
    Davos Platz is the central district of the Swiss Alpine town of Davos, known for hosting major international events and serving as a key hub for tourism and winter sports.
  • B. Schweizer Platz
    Schweizer Platz is a public square in Frankfurt am Main, Germany, known as a local hub in the Sachsenhausen district with shops, cafés, and access to the city’s U-Bahn network.
  • C. Bürkliplatz
    Bürkliplatz is a prominent square and transport hub on the shores of Lake Zurich, known for its lakeside promenade, boat pier, and popular markets.
  • D. Guisanplatz
    Guisanplatz is a prominent public square in Bern, Switzerland, named in honor of General Henri Guisan and serving as an important transport and civic hub.
  • E. Kagraner Platz
    Kagraner Platz is a public square and major transport hub in Vienna’s 22nd district, Donaustadt.
  • 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_69d8d395dba0819087568404508590cb completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e58d82297c81909f720e2637cec737 completed April 20, 2026, 2:20 a.m.
Created at: April 10, 2026, 11:52 a.m.