Triple

T35154486
Position Surface form Disambiguated ID Type / Status
Subject Kiesinger cabinet E1015080 entity
Predicate chancellorParty P100165 FINISHED
Object Christian Democratic Union of Germany 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: Christian Democratic Union of Germany | Statement: [Kiesinger cabinet, chancellorParty, Christian Democratic Union of Germany]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: chancellorParty
Context triple: [Kiesinger cabinet, chancellorParty, Christian Democratic Union of Germany]
  • A. hasPrimeMinisterOrChancellorFromParty chosen
    Indicates that an entity’s prime minister or chancellor belongs to (is a member of) a specified political party.
  • B. hasPrimeMinisterFromParty
    Indicates that a country or government has a serving prime minister who is a member of a specified political party.
  • C. typicalPrimeMinisterParty
    Indicates the political party that a prime minister is most commonly or characteristically associated with.
  • D. typicalDeputyPrimeMinisterParty
    Indicates the political party that a deputy prime minister is most commonly or characteristically affiliated with.
  • E. governingPartyOfState
    Indicates that a particular political party holds the primary governing authority over a given state.
  • F. None of above.

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_69f76ddb3a708190b521ba2970b17178 completed May 3, 2026, 3:46 p.m.
NER Named-entity recognition batch_69f78cf0cfdc81908da6f605f6988e8e completed May 3, 2026, 5:59 p.m.
PD Predicate disambiguation batch_69f78b9106008190930b3b3675b737d6 completed May 3, 2026, 5:53 p.m.
Created at: May 3, 2026, 4:02 p.m.