Triple
T4095979
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Global Cellulose Fibers |
E87821
|
entity |
| Predicate | brandOwner |
P347
|
FINISHED |
| Object | International Paper |
E15200
|
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: International Paper | Statement: [Global Cellulose Fibers, brandOwner, International Paper]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: International Paper Context triple: [Global Cellulose Fibers, brandOwner, International Paper]
-
A.
International Paper
chosen
International Paper is a leading global producer of renewable fiber-based packaging, pulp, and paper products.
-
B.
Georgia-Pacific
Georgia-Pacific is a major American pulp and paper company known for producing tissue, packaging, building products, and related chemicals.
-
C.
UPM
UPM is the Polytechnic University of Madrid, a leading Spanish public university specializing in engineering, architecture, and technology.
-
D.
K/O Paper Products
K/O Paper Products is a television and film production company best known for developing genre and science-fiction projects, including the TV series "Sleepy Hollow."
-
E.
Kimberly-Clark Corporation
Kimberly-Clark Corporation is a multinational personal care company best known for brands such as Kleenex, Huggies, and Scott paper products.
- 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_69aed94564cc8190a9c1457daedb6e7f |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefcddd76c81909fbf5db1f5d91a14 |
completed | March 9, 2026, 5:01 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5e4d20dd0819080773876f6198250 |
completed | March 14, 2026, 10:44 p.m. |
Created at: March 9, 2026, 3:40 p.m.