Triple

T4135980
Position Surface form Disambiguated ID Type / Status
Subject Mardi Gras E85155 entity
Predicate associatedWith P37 FINISHED
Object Georgia-Pacific consumer brands portfolio E14067 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: Georgia-Pacific consumer brands portfolio | Statement: [Mardi Gras, associatedWith, Georgia-Pacific consumer brands portfolio]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Georgia-Pacific consumer brands portfolio
Context triple: [Mardi Gras, associatedWith, Georgia-Pacific consumer brands portfolio]
  • A. Georgia-Pacific chosen
    Georgia-Pacific is a major American pulp and paper company known for producing tissue, packaging, building products, and related chemicals.
  • B. International Paper
    International Paper is a leading global producer of renewable fiber-based packaging, pulp, and paper products.
  • C. 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.
  • 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. UPM
    UPM is the Polytechnic University of Madrid, a leading Spanish public university specializing in engineering, architecture, and technology.
  • 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_69aed935ccd881909dc61f81bcdb7a78 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69af0233009881909333375d597b58b6 completed March 9, 2026, 5:24 p.m.
NED1 Entity disambiguation (via context triple) batch_69b576c75e5c8190acc4ee72cb574432 completed March 14, 2026, 2:55 p.m.
Created at: March 9, 2026, 3:43 p.m.