Triple

T21716976
Position Surface form Disambiguated ID Type / Status
Subject Altstadt (Zürich) E536055 entity
Predicate contains P35 FINISHED
Object Lindenhof hill 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: Lindenhof hill | Statement: [Altstadt (Zürich), contains, Lindenhof hill]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lindenhof hill
Context triple: [Altstadt (Zürich), contains, Lindenhof hill]
  • A. Lindenhof hill chosen
    Lindenhof hill is a historic elevated park in Zurich offering panoramic views over the Old Town and the Limmat River.
  • B. Lindenhof
    Lindenhof is a locality or neighborhood that forms part of the town of Oberndorf am Neckar in the German state of Baden-Württemberg.
  • C. Marienberg hill
    Marienberg hill is a prominent elevation overlooking Würzburg, Germany, best known as the site of the historic Marienberg Fortress.
  • D. Burghölzli hill
    Burghölzli hill is a prominent elevation in Zurich, Switzerland, known for hosting the historic Burghölzli psychiatric hospital associated with the University of Zurich.
  • E. Hönggerberg hill
    Hönggerberg hill is a prominent elevation in Zurich, Switzerland, known for hosting part of ETH Zurich’s science and technology campus and offering views over the city and the Limmat Valley.
  • 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_69e0c46c6dd88190a595375fa6ebd701 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69efd96ab4c88190b76f4a6b7c855039 completed April 27, 2026, 9:47 p.m.
Created at: April 16, 2026, 6:47 p.m.