Triple

T9711443
Position Surface form Disambiguated ID Type / Status
Subject Sunila Pulp Mill and residential area E235030 entity
Predicate laterOwner P12936 FINISHED
Object Stora Enso E681817 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: Stora Enso | Statement: [Sunila Pulp Mill and residential area, laterOwner, Stora Enso]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Stora Enso
Context triple: [Sunila Pulp Mill and residential area, laterOwner, Stora Enso]
  • A. Stora Enso chosen
    Stora Enso is a Finnish-Swedish renewable materials and packaging company and one of the world’s largest producers of paper, pulp, and wood products.
  • B. UPM
    UPM is the Polytechnic University of Madrid, a leading Spanish public university specializing in engineering, architecture, and technology.
  • C. Roseburg Forest Products
    Roseburg Forest Products is a privately owned wood products company based in Roseburg, Oregon, known for manufacturing lumber, engineered wood, and other building materials.
  • D. International Paper
    International Paper is a leading global producer of renewable fiber-based packaging, pulp, and paper products.
  • E. Georgia-Pacific
    Georgia-Pacific is a major American pulp and paper company known for producing tissue, packaging, building products, and related chemicals.
  • 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_69ca84cd8fa0819090a5e243ceb37003 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cd9e0591208190aa57cc9e2aebafb7 completed April 1, 2026, 10:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69d19f8c26dc8190a6fa21bde27ba6fa completed April 4, 2026, 11:32 p.m.
Created at: March 30, 2026, 8:19 p.m.