Triple

T16515031
Position Surface form Disambiguated ID Type / Status
Subject Danish Broadcasting Corporation E401159 entity
Predicate hasOnlineService P57 FINISHED
Object dr.dk E1121557 NE FINISHED

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: dr.dk | Statement: [Danish Broadcasting Corporation, hasOnlineService, dr.dk]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: dr.dk
Context triple: [Danish Broadcasting Corporation, hasOnlineService, dr.dk]
  • A. DANSKE
    DANSKE is the stock ticker symbol for Danske Bank, a major Nordic financial services group headquartered in Denmark.
  • B. DR Byen chosen
    DR Byen is the headquarters and main production complex of the Danish Broadcasting Corporation in Copenhagen, known for its modern architecture and major media facilities.
  • C. Danish Days
    Danish Days is an annual cultural festival in Solvang, California that celebrates the town’s Danish heritage with traditional food, music, dancing, and parades.
  • D. Banedanmark
    Banedanmark is the Danish government agency responsible for owning, maintaining, and managing most of Denmark’s railway infrastructure.
  • E. Krøderen
    Krøderen is a long, narrow lake in Viken county, Norway, known for its scenic surroundings and the heritage Krøder Line railway running along its shore.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d883838abc8190bc79cb2d41733ce2 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e32e7a5ff88190984e2f2bc2fd17cc completed April 18, 2026, 7:10 a.m.
NED1 Entity disambiguation (via context triple) batch_6a006084949081909e8cdfeafa7564de completed May 10, 2026, 10:40 a.m.
Created at: April 10, 2026, 5:14 a.m.