Triple

T21975460
Position Surface form Disambiguated ID Type / Status
Subject VTB Insurance E542692 entity
Predicate hasCompetitor P1375 FINISHED
Object SOGAZ
SOGAZ is one of Russia’s largest insurance companies, offering a wide range of insurance and financial risk management services to corporate and retail clients.
 E1510734 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: SOGAZ | Statement: [VTB Insurance, hasCompetitor, SOGAZ]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SOGAZ
Context triple: [VTB Insurance, hasCompetitor, SOGAZ]
  • A. Sogoo
    Sogoo is an alternative name for the Omotik language spoken by the Omotik people of Kenya.
  • B. Socar
    Socar is an ancient Egyptian funerary deity associated with the Memphite necropolis and the afterlife, often later syncretized with Ptah and Osiris.
  • C. So.G.Aer S.p.A.
    So.G.Aer S.p.A. is the company responsible for managing and operating Cagliari Elmas Airport in Sardinia, Italy.
  • D. Sogea-Satom
    Sogea-Satom is a construction and civil engineering company operating primarily in Africa, specializing in infrastructure projects such as roads, bridges, and public works.
  • E. Sogecine
    Sogecine is a Spanish film production company known for backing acclaimed auteur-driven cinema, including works by director Alejandro Amenábar.
  • 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: SOGAZ
Triple: [VTB Insurance, hasCompetitor, SOGAZ]
Generated description
SOGAZ is one of Russia’s largest insurance companies, offering a wide range of insurance and financial risk management services to corporate and retail clients.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SOGAZ
Target entity description: SOGAZ is one of Russia’s largest insurance companies, offering a wide range of insurance and financial risk management services to corporate and retail clients.
  • A. Sogoo
    Sogoo is an alternative name for the Omotik language spoken by the Omotik people of Kenya.
  • B. Socar
    Socar is an ancient Egyptian funerary deity associated with the Memphite necropolis and the afterlife, often later syncretized with Ptah and Osiris.
  • C. So.G.Aer S.p.A.
    So.G.Aer S.p.A. is the company responsible for managing and operating Cagliari Elmas Airport in Sardinia, Italy.
  • D. Sogea-Satom
    Sogea-Satom is a construction and civil engineering company operating primarily in Africa, specializing in infrastructure projects such as roads, bridges, and public works.
  • E. Sogecine
    Sogecine is a Spanish film production company known for backing acclaimed auteur-driven cinema, including works by director Alejandro Amenábar.
  • 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_69e0c48070988190909db97667b9a0ac completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f124886418819091daed0988432350 completed April 28, 2026, 9:20 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0a671abb648190b9a4cc67c733f356 completed May 18, 2026, 1:10 a.m.
NEDg Description generation batch_6a0a6812112c81909844ab725dff79ed completed May 18, 2026, 1:14 a.m.
NED2 Entity disambiguation (via description) batch_6a0a68846fb88190bbe1510608aa9468 completed May 18, 2026, 1:16 a.m.
Created at: April 16, 2026, 8:03 p.m.