Triple

T4095980
Position Surface form Disambiguated ID Type / Status
Subject Global Cellulose Fibers E87821 entity
Predicate hasParentOrganization P10 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, hasParentOrganization, International Paper]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: International Paper
Context triple: [Global Cellulose Fibers, hasParentOrganization, 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_69b5f5a4f75481909236504eaf81ce33 completed March 14, 2026, 11:56 p.m.
Created at: March 9, 2026, 3:40 p.m.