Triple

T22259662
Position Surface form Disambiguated ID Type / Status
Subject Wernigerode Castle E550183 entity
Predicate near P350 FINISHED
Object Brocken mountain 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: Brocken mountain | Statement: [Wernigerode Castle, near, Brocken mountain]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Brocken mountain
Context triple: [Wernigerode Castle, near, Brocken mountain]
  • A. Brocken chosen
    Brocken is a prominent mountain in central Germany’s Harz range, known for its harsh climate, folklore, and role in literature and cultural history.
  • B. Bärenkopf
    Bärenkopf is a mountain peak in the Austrian Alps that forms part of the Glockner Group.
  • C. Teufelstättkopf
    Teufelstättkopf is a mountain peak in the Bavarian Ammergau Alps, popular with hikers for its scenic views and relatively accessible trails.
  • D. Eichberg
    Eichberg is a municipality in the Swiss canton of St. Gallen, situated in the Rhine Valley region near the border with Austria.
  • E. Wendelstein mountain
    Wendelstein mountain is a prominent peak in the Bavarian Alps of southern Germany, known for its panoramic views, observatory, and historic cogwheel railway.
  • 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_69e11e42adb8819087714772ea606709 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f138c5b54c8190854690ba599639fa completed April 28, 2026, 10:46 p.m.
Created at: April 16, 2026, 8:39 p.m.