Triple

T15215980
Position Surface form Disambiguated ID Type / Status
Subject ORF E363636 entity
Predicate offersService P178 FINISHED
Object ORF TVthek E1062652 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: ORF TVthek | Statement: [ORF, offersService, ORF TVthek]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ORF TVthek
Context triple: [ORF, offersService, ORF TVthek]
  • A. ORF TVthek chosen
    ORF TVthek is the Austrian Broadcasting Corporation’s online video platform offering on-demand access to its television programs and live streams.
  • B. ORF
    ORF is Austria's national public service broadcaster, operating multiple television and radio channels as well as online services.
  • C. ORF
    ORF is the three-letter IATA airport code for Norfolk International Airport in Norfolk, Virginia.
  • D. ZDFmediathek
    ZDFmediathek is the online streaming and on-demand media platform of the German public broadcaster ZDF, offering access to its TV programs, series, films, and live streams.
  • E. Österreichischer Rundfunk
    Österreichischer Rundfunk is Austria’s national public broadcasting organization, operating multiple television, radio, and online services.
  • 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_69d85a0b78bc8190b6e5ad51a2c4cfc5 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e0076e4348819091fa91c1562e7c5c completed April 15, 2026, 9:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69fed343f51481908f04c35d37b39ad2 completed May 9, 2026, 6:25 a.m.
Created at: April 10, 2026, 3:11 a.m.