Triple

T18595750
Position Surface form Disambiguated ID Type / Status
Subject Social Code Book I E454488 entity
Predicate relatedTo P37 FINISHED
Object Social Code Book VI — 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: Social Code Book VI | Statement: [Social Code Book I, relatedTo, Social Code Book VI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Social Code Book VI
Context triple: [Social Code Book I, relatedTo, Social Code Book VI]
  • A. Social Code Book VI chosen
    Social Code Book VI is the German federal statute that comprehensively regulates the public old-age, disability, and survivors’ pension insurance system.
  • B. Social Code Book IV
    Social Code Book IV is a key component of Germany’s social security legislation that governs unemployment insurance and job placement services.
  • C. Social Code Book VII
    Social Code Book VII is a volume of German social law that governs statutory accident insurance and related occupational injury protections.
  • D. Social Code Book XII
    Social Code Book XII is a component of Germany’s codified social law that regulates specific aspects of the country’s social security and welfare system.
  • E. Social Code Book III
    Social Code Book III is a key component of Germany’s social security legislation that regulates statutory health insurance and related healthcare benefits.
  • 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_69d8d38ae7e081908a98df1251842402 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e545ba3bc881908f5308e09d54e05b completed April 19, 2026, 9:14 p.m.
Created at: April 10, 2026, 11:44 a.m.