Triple

T10413294
Position Surface form Disambiguated ID Type / Status
Subject SAS Group E245448 entity
Predicate hasSubsidiary P254 FINISHED
Object SAS Cargo Group E862142 NE FINISHED

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: SAS Cargo Group | Statement: [SAS Group, hasSubsidiary, SAS Cargo Group]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: SAS Cargo Group
Context triple: [SAS Group, hasSubsidiary, SAS Cargo Group]
  • A. SAS Cargo chosen
    SAS Cargo is the air freight and cargo division of Scandinavian Airlines, providing cargo transport and logistics services across the airline’s route network.
  • B. ANA Cargo Inc.
    ANA Cargo Inc. is the air freight and logistics arm of Japan’s All Nippon Airways group, providing international and domestic cargo transport services.
  • C. Lufthansa Cargo
    Lufthansa Cargo is the air freight and logistics division of the Lufthansa Group, operating a global network for transporting cargo by air.
  • D. Kuehne + Nagel
    Kuehne + Nagel is a global logistics and freight forwarding company specializing in sea, air, and contract logistics services.
  • E. Northern Air Cargo
    Northern Air Cargo is an Alaska-based cargo airline specializing in freight services across Alaska and to destinations in the continental United States.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d381be340c8190b05998703d42d224 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4ea0ec6fc8190a71af759226a3cba completed April 7, 2026, 11:27 a.m.
NED1 Entity disambiguation (via context triple) batch_69d87e9b86648190b83eb5261c9a7b97 completed April 10, 2026, 4:37 a.m.
Created at: April 6, 2026, 12:10 p.m.