Triple

T4095909
Position Surface form Disambiguated ID Type / Status
Subject IP E87819 entity
Predicate associatedCompany P629 FINISHED
Object International Paper Company 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 Company | Statement: [IP, associatedCompany, International Paper Company]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: International Paper Company
Context triple: [IP, associatedCompany, International Paper Company]
  • 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. Weyerhaeuser Company
    Weyerhaeuser Company is a major American timberland and forest products company, historically one of the world’s largest private owners of softwood timber.
  • 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_69b589d825c48190b4208b0502c257bb completed March 14, 2026, 4:16 p.m.
Created at: March 9, 2026, 3:40 p.m.