Triple

T21775496
Position Surface form Disambiguated ID Type / Status
Subject Green Cargo E537561 entity
Predicate subsidiary P258 FINISHED
Object Green Cargo Denmark 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: Green Cargo Denmark | Statement: [Green Cargo, subsidiary, Green Cargo Denmark]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Green Cargo Denmark
Context triple: [Green Cargo, subsidiary, Green Cargo Denmark]
  • A. Green Cargo chosen
    Green Cargo is a Swedish state-owned rail freight company that provides cargo transport services across Scandinavia and parts of Europe.
  • B. HK Danmark
    HK Danmark is one of Denmark’s major trade unions, representing a wide range of clerical, administrative, and service sector employees.
  • C. Ennore Container Terminal
    Ennore Container Terminal is a major marine cargo facility near Chennai, India, specializing in handling containerized trade as part of the country’s expanding port infrastructure.
  • D. New Denmark
    New Denmark is a rural community in Victoria County, New Brunswick, known for its strong Danish heritage and agricultural roots.
  • E. Port of Odense
    The Port of Odense is a major Danish commercial and industrial seaport on the island of Funen, known for shipbuilding, offshore wind activities, and maritime logistics.
  • 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_69e0c470759c819094a215757113562b completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69f046291d808190b5111a8d4819909f completed April 28, 2026, 5:31 a.m.
Created at: April 16, 2026, 6:51 p.m.