Triple

T17481173
Position Surface form Disambiguated ID Type / Status
Subject Atlas Air E425661 entity
Predicate operatesFor P3679 FINISHED
Object DHL NE NERFINISHED

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: DHL | Statement: [Atlas Air, operatesFor, DHL]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: DHL
Context triple: [Atlas Air, operatesFor, DHL]
  • A. DHL
    DHL is the Dag Hammarskjöld Library, the United Nations’ main research and information resource center located at its headquarters in New York.
  • B. DHL chosen
    DHL is a global logistics and courier company known for its international express mail, freight transportation, and supply chain management services.
  • C. TNT Express
    TNT Express is an international courier and logistics company known for its global parcel delivery and express mail services.
  • D. FedEx
    FedEx is a global courier delivery services company known for its overnight shipping and pioneering real-time package tracking.
  • E. StarTrack
    StarTrack is an Australian logistics and freight company specializing in parcel delivery and express transport services.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d889dccf7481909264a1844a2e9100 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e451bfd75481908c20bc2c1cbff593 completed April 19, 2026, 3:53 a.m.
Created at: April 10, 2026, 5:48 a.m.