Triple

T20309918
Position Surface form Disambiguated ID Type / Status
Subject heute E510209 entity
Predicate hasSpinOff P7226 FINISHED
Object heute-journal 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: heute-journal | Statement: [heute, hasSpinOff, heute-journal]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: heute-journal
Context triple: [heute, hasSpinOff, heute-journal]
  • A. heute-journal chosen
    heute-journal is a prominent German television news magazine that provides in-depth reporting and analysis of current national and international events on the public broadcaster ZDF.
  • B. heute (news program)
    "heute" is a long-running German television news program that serves as one of the main daily newscasts on the public broadcaster ZDF.
  • C. tagesschau24
    tagesschau24 is a German public television news channel focusing on continuous news coverage, background reports, and live event broadcasts.
  • D. Daily News Live
    Daily News Live was a long-running Philadelphia sports talk and analysis television program featuring discussions, interviews, and commentary on local and national sports.
  • E. Berita Harian
    Berita Harian is a major Malay-language daily newspaper in Malaysia known for its national news coverage and wide readership.
  • 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_69e0b4c7491c8190961113c4283b10b0 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e677436af88190a046c44fa45b68b4 completed April 20, 2026, 6:58 p.m.
Created at: April 16, 2026, 11:18 a.m.