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.