Triple

T25641566

Position	Surface form	Disambiguated ID	Type / Status
Subject	Ste. Michelle Wine Estates	`E642849`	entity
Predicate	wasSubsidiaryOf	`P20316`	FINISHED
Object	U.S. Tobacco U.S. Tobacco is an American company best known as a major producer and marketer of smokeless tobacco products.	`E1721394`	NE FINISHED

How this triple was built (3 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: U.S. Tobacco | Statement: [Ste. Michelle Wine Estates, wasSubsidiaryOf, U.S. Tobacco]

NEDg Description generation gpt-5.1

Instruction

Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"

Input

Entity: U.S. Tobacco
Triple: [Ste. Michelle Wine Estates, wasSubsidiaryOf, U.S. Tobacco]

Generated description

U.S. Tobacco is an American company best known as a major producer and marketer of smokeless tobacco products.

PD Predicate disambiguation gpt-5-mini-2025-08-07

Target predicate: wasSubsidiaryOf
Context triple: [Ste. Michelle Wine Estates, wasSubsidiaryOf, U.S. Tobacco]

A. hasAllianceThroughSubsidiary
Indicates that two entities are in an alliance indirectly, established or maintained through one or more subsidiary entities rather than directly between the primary entities.
B. hasParentCompany chosen
Indicates that one company is owned or controlled by another company that serves as its parent organization.
C. usedBySubsidiaryOf
Indicates that something is used by an entity that is a subsidiary of another organization.
D. foundedAsHoldingCompanyFor
Indicates that an entity was originally established specifically to serve as a holding company for another entity or group of entities.
E. notableSubsidiary
Indicates that one entity is a subsidiary of another and is particularly significant or prominent among that parent’s subsidiaries.
F. None of above.

Provenance (6 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_69e77e7ce28081908b08d65ee6e5c8be`	completed	April 21, 2026, 1:41 p.m.
NER	Named-entity recognition	`batch_69f5fa660fa0819087e2711cee51d7a1`	completed	May 2, 2026, 1:21 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a119a2d16c0819085170b61dd30bc11`	completed	May 23, 2026, 12:14 p.m.
NEDg	Description generation	`batch_6a119b9ccb58819083a8df3cc389c790`	completed	May 23, 2026, 12:20 p.m.
NED2	Entity disambiguation (via description)	`batch_6a119c7d5eac8190ae6fbb97bf64b472`	completed	May 23, 2026, 12:24 p.m.
PD	Predicate disambiguation	`batch_69f4807f8680819098a524158d049c63`	completed	May 1, 2026, 10:29 a.m.

Created at: April 21, 2026, 5:43 p.m.