Triple

T4578074
Position Surface form Disambiguated ID Type / Status
Subject Social Code Book V E101787 entity
Predicate shortName P43 FINISHED
Object SGB V
SGB V is the German Social Code Book V, the central legal framework governing statutory health insurance in Germany.
 E453551 NE FINISHED

How this triple was built (4 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: SGB V | Statement: [Social Code Book V, shortName, SGB V]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SGB V
Context triple: [Social Code Book V, shortName, SGB V]
  • A. SGC
    SGC is the station code for St George's Cross, a Glasgow Subway station in Scotland.
  • B. VJ
    VJ is the abbreviation for the Yugoslav Army, the armed forces of the former Federal Republic of Yugoslavia active during the 1990s and early 2000s.
  • C. GVB
    GVB is Amsterdam’s primary public transport company, operating the city’s trams, buses, metro, and ferries.
  • D. VJRA
    VJRA is a U.S. federal law that established judicial review of veterans’ benefits decisions, creating a specialized court system to handle appeals from the Department of Veterans Affairs.
  • E. VBG
    VBG is the abbreviated name of the German association of botanical gardens, Verband Botanischer Gärten e.V.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: SGB V
Triple: [Social Code Book V, shortName, SGB V]
Generated description
SGB V is the German Social Code Book V, the central legal framework governing statutory health insurance in Germany.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SGB V
Target entity description: SGB V is the German Social Code Book V, the central legal framework governing statutory health insurance in Germany.
  • A. SGC
    SGC is the station code for St George's Cross, a Glasgow Subway station in Scotland.
  • B. VJ
    VJ is the abbreviation for the Yugoslav Army, the armed forces of the former Federal Republic of Yugoslavia active during the 1990s and early 2000s.
  • C. GVB
    GVB is Amsterdam’s primary public transport company, operating the city’s trams, buses, metro, and ferries.
  • D. VJRA
    VJRA is a U.S. federal law that established judicial review of veterans’ benefits decisions, creating a specialized court system to handle appeals from the Department of Veterans Affairs.
  • E. VBG
    VBG is the abbreviated name of the German association of botanical gardens, Verband Botanischer Gärten e.V.
  • F. None of above. chosen

Provenance (5 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_69bd43d4ce208190b53158c882b222e3 completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd58e2a1808190be4582d5b3003d6c completed March 20, 2026, 2:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69bdd3ee510481909d481b157bd0b2bd completed March 20, 2026, 11:10 p.m.
NEDg Description generation batch_69bdd5a85488819092a4a7cc4f58a425 completed March 20, 2026, 11:18 p.m.
NED2 Entity disambiguation (via description) batch_69bdd63370088190adca99373f83374f completed March 20, 2026, 11:20 p.m.
Created at: March 20, 2026, 1:10 p.m.