Triple

T326754
Position Surface form Disambiguated ID Type / Status
Subject KGB E6535 entity
Predicate followedBy P78 FINISHED
Object SVR
SVR is Russia’s primary foreign intelligence service, which succeeded the Soviet-era KGB’s external intelligence functions after the USSR’s dissolution.
 E41755 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: SVR | Statement: [KGB, followedBy, SVR]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SVR
Context triple: [KGB, followedBy, SVR]
  • A. SV
    SV is the two-letter ISO 3166-1 alpha-2 country code assigned to El Salvador.
  • B. RVR
    RVR is the standard abbreviation for the Reina-Valera, a widely used Spanish translation of the Bible.
  • C. SLV
    SLV is the three-letter ISO 3166-1 alpha-3 country code assigned to El Salvador.
  • D. Sark
    Sark is a small, car-free island in the English Channel known for its rugged coastline, traditional feudal-style governance history, and designation as a Dark Sky Island.
  • E. VELO
    VELO is the high-precision vertex detector of the LHCb experiment at CERN, designed to measure particle trajectories very close to the proton–proton collision point.
  • 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: SVR
Triple: [KGB, followedBy, SVR]
Generated description
SVR is Russia’s primary foreign intelligence service, which succeeded the Soviet-era KGB’s external intelligence functions after the USSR’s dissolution.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SVR
Target entity description: SVR is Russia’s primary foreign intelligence service, which succeeded the Soviet-era KGB’s external intelligence functions after the USSR’s dissolution.
  • A. SV
    SV is the two-letter ISO 3166-1 alpha-2 country code assigned to El Salvador.
  • B. RVR
    RVR is the standard abbreviation for the Reina-Valera, a widely used Spanish translation of the Bible.
  • C. SLV
    SLV is the three-letter ISO 3166-1 alpha-3 country code assigned to El Salvador.
  • D. Sark
    Sark is a small, car-free island in the English Channel known for its rugged coastline, traditional feudal-style governance history, and designation as a Dark Sky Island.
  • E. VELO
    VELO is the high-precision vertex detector of the LHCb experiment at CERN, designed to measure particle trajectories very close to the proton–proton collision point.
  • 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_69a2e7933d6c8190bb2592ad13286ef2 completed Feb. 28, 2026, 1:03 p.m.
NER Named-entity recognition batch_69a2ea974d8481908c7d84f72a7728b6 completed Feb. 28, 2026, 1:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69a3cfedb8a4819085970bddbd8ff9c1 completed March 1, 2026, 5:34 a.m.
NEDg Description generation batch_69a3d0575f588190990388e957d78847 completed March 1, 2026, 5:36 a.m.
NED2 Entity disambiguation (via description) batch_69a3d0e13d3c8190b5618ddb66492f41 completed March 1, 2026, 5:38 a.m.
Created at: Feb. 28, 2026, 1:08 p.m.