Triple

T8741833
Position Surface form Disambiguated ID Type / Status
Subject S7 Group E207520 entity
Predicate ownsSubsidiary P9212 FINISHED
Object S7 Technics
S7 Technics is a Russian aircraft maintenance, repair, and overhaul (MRO) company that services both S7 Airlines and other carriers.
E754446 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: S7 Technics | Statement: [S7 Group, ownsSubsidiary, S7 Technics]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: S7 Technics
Context triple: [S7 Group, ownsSubsidiary, S7 Technics]
  • A. S7
    S7 is a Berlin S-Bahn rapid transit line that runs across the city, connecting key districts between Potsdam and Ahrensfelde.
  • B. S7
    S7 is the IATA airline designator for S7 Airlines, a major Russian carrier based in Novosibirsk.
  • C. Siemens S70
    The Siemens S70 is a modern low-floor light rail vehicle widely used in North American urban transit systems.
  • D. Siemens SD100
    The Siemens SD100 is a light rail vehicle model built by Siemens for use on urban trolley and light rail systems such as the San Diego Trolley.
  • E. Siemens SD-160
    The Siemens SD-160 is a high-floor light rail vehicle widely used in North American transit systems, including Calgary’s CTrain, known for its modular design and reliable urban service.
  • 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: S7 Technics
Triple: [S7 Group, ownsSubsidiary, S7 Technics]
Generated description
S7 Technics is a Russian aircraft maintenance, repair, and overhaul (MRO) company that services both S7 Airlines and other carriers.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: S7 Technics
Target entity description: S7 Technics is a Russian aircraft maintenance, repair, and overhaul (MRO) company that services both S7 Airlines and other carriers.
  • A. S7
    S7 is the IATA airline designator for S7 Airlines, a major Russian carrier based in Novosibirsk.
  • B. S7
    S7 is a Berlin S-Bahn rapid transit line that runs across the city, connecting key districts between Potsdam and Ahrensfelde.
  • C. Siemens S70
    The Siemens S70 is a modern low-floor light rail vehicle widely used in North American urban transit systems.
  • D. Siemens SD100
    The Siemens SD100 is a light rail vehicle model built by Siemens for use on urban trolley and light rail systems such as the San Diego Trolley.
  • E. Siemens SD-160
    The Siemens SD-160 is a high-floor light rail vehicle widely used in North American transit systems, including Calgary’s CTrain, known for its modular design and reliable urban service.
  • 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_69ca835a03a081909d4d4cd01a18c9fb completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc5d6fd5dc8190906b7147f27c5d46 completed March 31, 2026, 11:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69cf42f282e48190ad158063e265e0f0 completed April 3, 2026, 4:32 a.m.
NEDg Description generation batch_69cf4433605c8190991f95d19726cab8 completed April 3, 2026, 4:38 a.m.
NED2 Entity disambiguation (via description) batch_69cf44c20b408190b622d18f78277802 completed April 3, 2026, 4:40 a.m.
Created at: March 30, 2026, 6:38 p.m.