Triple

T7813588
Position Surface form Disambiguated ID Type / Status
Subject EDDB E180744 entity
Predicate hasFocusCityFor P1295 FINISHED
Object Lufthansa E48740 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: Lufthansa | Statement: [EDDB, hasFocusCityFor, Lufthansa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lufthansa
Context triple: [EDDB, hasFocusCityFor, Lufthansa]
  • A. Lufthansa chosen
    Lufthansa is Germany’s largest airline and a major global carrier known for its extensive international network and role in shaping modern airline alliances.
  • B. Lufthansa Cargo
    Lufthansa Cargo is the air freight and logistics division of the Lufthansa Group, operating a global network for transporting cargo by air.
  • C. Interflug
    Interflug was the state-owned national airline of East Germany, operating international and domestic flights primarily within the Eastern Bloc during the Cold War.
  • D. S7 Airlines
    S7 Airlines is a major Russian airline based in Novosibirsk that operates extensive domestic and international routes, particularly across Russia, Europe, and Asia.
  • E. Lufthansa CityLine
    Lufthansa CityLine is a German regional airline and Lufthansa subsidiary that operates short- and medium-haul routes across Europe, primarily feeding traffic into Lufthansa’s main hubs.
  • 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_69ca827f6f148190beca4e245b993506 completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69caf78f3d6481909841d64117f657e1 completed March 30, 2026, 10:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69cb5a5048a88190874d7ff205151d8a completed March 31, 2026, 5:23 a.m.
Created at: March 30, 2026, 4:38 p.m.