Triple

T15683345
Position Surface form Disambiguated ID Type / Status
Subject Heather Kadin E377633 entity
Predicate employer P7 FINISHED
Object K/O Paper Products E347336 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: K/O Paper Products | Statement: [Heather Kadin, employer, K/O Paper Products]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: K/O Paper Products
Context triple: [Heather Kadin, employer, K/O Paper Products]
  • A. K/O Paper Products chosen
    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."
  • B. McNamara Paper Products
    McNamara Paper Products is a production company known for its involvement in creating film and television projects such as "Fastlane."
  • C. Irving Tissue
    Irving Tissue is a North American manufacturer of tissue and paper products, known for producing household paper brands as part of the J.D. Irving group of companies.
  • D. International Paper
    International Paper is a leading global producer of renewable fiber-based packaging, pulp, and paper products.
  • 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_69d85cd2e28481909d4e975bee20872f completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04f31b5b881908e46ecd9fc6048ab completed April 16, 2026, 2:53 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff6ee4c8688190ae2fefb56171161a completed May 9, 2026, 5:29 p.m.
Created at: April 10, 2026, 4:17 a.m.