Triple

T7510212
Position Surface form Disambiguated ID Type / Status
Subject DHL Aviation E177498 entity
Predicate notableSubsidiaryAirlines P9212 FINISHED
Object AeroLogic
AeroLogic is a German cargo airline operating long-haul freight services, primarily on behalf of DHL and Lufthansa Cargo.
 E670264 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: AeroLogic | Statement: [DHL Aviation, notableSubsidiaryAirlines, AeroLogic]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: AeroLogic
Context triple: [DHL Aviation, notableSubsidiaryAirlines, AeroLogic]
  • A. AeroMass
    AeroMass is an aviation-related organization associated with Wings, likely involved in providing air services or support within the aerospace sector.
  • B. Ramport Aero
    Ramport Aero is the company responsible for managing and operating Zhukovsky International Airport near Moscow, Russia.
  • C. Canair
    Canair was a Spanish regional airline that operated inter-island flights in the Canary Islands.
  • D. IrAero
    IrAero is a Russian regional airline that operates passenger and cargo flights across Siberia, the Russian Far East, and neighboring countries.
  • E. Aero
    Aero is a high-performance, sport-oriented trim level used by Saab for its 9-3 and other models, typically featuring more powerful engines and upgraded equipment.
  • 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: AeroLogic
Triple: [DHL Aviation, notableSubsidiaryAirlines, AeroLogic]
Generated description
AeroLogic is a German cargo airline operating long-haul freight services, primarily on behalf of DHL and Lufthansa Cargo.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: AeroLogic
Target entity description: AeroLogic is a German cargo airline operating long-haul freight services, primarily on behalf of DHL and Lufthansa Cargo.
  • A. AeroMass
    AeroMass is an aviation-related organization associated with Wings, likely involved in providing air services or support within the aerospace sector.
  • B. Ramport Aero
    Ramport Aero is the company responsible for managing and operating Zhukovsky International Airport near Moscow, Russia.
  • C. Canair
    Canair was a Spanish regional airline that operated inter-island flights in the Canary Islands.
  • D. IrAero
    IrAero is a Russian regional airline that operates passenger and cargo flights across Siberia, the Russian Far East, and neighboring countries.
  • E. Aero
    Aero is a high-performance, sport-oriented trim level used by Saab for its 9-3 and other models, typically featuring more powerful engines and upgraded equipment.
  • 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_69c69f276b108190af2cc790b6554544 completed March 27, 2026, 3:15 p.m.
NER Named-entity recognition batch_69c7017134608190bd51fb2d0ab1ff34 completed March 27, 2026, 10:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8461035b48190ba08c0f759cafe4a completed March 28, 2026, 9:20 p.m.
NEDg Description generation batch_69c84754ec048190be1e37c2189b56ed completed March 28, 2026, 9:25 p.m.
NED2 Entity disambiguation (via description) batch_69c848026e90819098d0b419101f91e1 completed March 28, 2026, 9:28 p.m.
Created at: March 27, 2026, 3:45 p.m.