Triple

T599310
Position Surface form Disambiguated ID Type / Status
Subject Petro Poroshenko E11457 entity
Predicate founded P104 FINISHED
Object Roshen E74690 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: Roshen | Statement: [Petro Poroshenko, founded, Roshen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Roshen
Context triple: [Petro Poroshenko, founded, Roshen]
  • A. Roshen chosen
    Roshen is a major Ukrainian confectionery corporation known for producing a wide range of chocolates, candies, and other sweets and for being one of Eastern Europe’s largest candy manufacturers.
  • B. Lovefeast
    Lovefeast is a Christian communal meal and worship service, especially associated with Moravian and some Methodist traditions, that emphasizes fellowship, shared food, and spiritual unity rather than the sacramental elements of Holy Communion.
  • C. Kraft
    Kraft is a prominent American surname most widely associated with billionaire businessman and New England Patriots owner Robert Kraft.
  • D. Nestlé
    Nestlé is a Swiss multinational food and beverage conglomerate and one of the world’s largest consumer goods companies.
  • E. Heinz
    Heinz is the German given name of Henry Alfred Kissinger, the influential American diplomat and former U.S. Secretary of State.
  • 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_69a4932779b881908688590d59c71900 completed March 1, 2026, 7:27 p.m.
NER Named-entity recognition batch_69a49d78c0f08190b83ad89062ccb0b9 completed March 1, 2026, 8:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69a5216e11248190a8c564a482d649a6 completed March 2, 2026, 5:34 a.m.
Created at: March 1, 2026, 7:35 p.m.