Triple

T18644937
Position Surface form Disambiguated ID Type / Status
Subject Carlsberg Group E455779 entity
Predicate brand P1500 FINISHED
Object Hof 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: Hof | Statement: [Carlsberg Group, brand, Hof]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hof
Context triple: [Carlsberg Group, brand, Hof]
  • A. Hof
    Hof is a small settlement within the municipality of Lutzenberg in the Swiss canton of Appenzell Ausserrhoden.
  • B. Hof chosen
    Hof is a town in northeastern Bavaria, Germany, known for its location near the Czech border and its regional cultural and economic significance.
  • C. Heimhof
    Heimhof is a notable residential building in Vienna, Austria, designed in the early 20th century by architect Hubert Gessner in a distinctive Viennese Secessionist style.
  • D. Walddorf
    Walddorf is a village-level subdivision of the town of Altensteig in the state of Baden-Württemberg, Germany.
  • E. Heiderhof
    Heiderhof is a residential subdistrict of the Bonn borough Bad Godesberg in western Germany.
  • 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_69d8d38ea1e88190997e9b231190ba6f completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e5500c36188190bfdd7aca73f3c006 completed April 19, 2026, 9:58 p.m.
Created at: April 10, 2026, 11:47 a.m.