Triple

T19985998
Position Surface form Disambiguated ID Type / Status
Subject Lori Black E493932 entity
Predicate notableWork P4 FINISHED
Object Lysol NE NERFINISHED

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: Lysol | Statement: [Lori Black, notableWork, Lysol]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lysol
Context triple: [Lori Black, notableWork, Lysol]
  • A. Lysol chosen
    Lysol is a well-known brand of household disinfectant and cleaning products widely used for sanitizing surfaces and killing germs.
  • B. Domestos
    Domestos is a widely sold household cleaning and disinfectant brand known for its powerful bleach-based products.
  • C. Dettol
    Dettol is a widely used antiseptic and disinfectant brand known for its germ-killing cleaning and personal hygiene products.
  • D. Clorox
    Clorox is a major American consumer goods company best known for its household cleaning and disinfecting products, including its flagship bleach brand.
  • E. Windex
    Windex is a popular household cleaning product best known for its blue glass cleaner used on windows and other hard surfaces.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69da626a67648190af9653832a3aeced completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e65d16f60c81909ba02c0a3429ecae completed April 20, 2026, 5:06 p.m.
Created at: April 11, 2026, 3:29 p.m.