Triple

T29471945

Position	Surface form	Disambiguated ID	Type / Status
Subject	Служебный роман	`E747531`	entity
Predicate	актёр	`P5563`	FINISHED
Object	Андрей Мягков Андрей Мягков — советский и российский актёр театра и кино, наиболее известный по своим ролям в лирических комедиях Эльдара Рязанова, включая «Иронию судьбы» и «Служебный роман».	`E1878199`	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: Андрей Мягков | Statement: [Служебный роман, актёр, Андрей Мягков]

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: Андрей Мягков
Triple: [Служебный роман, актёр, Андрей Мягков]

Generated description

Андрей Мягков — советский и российский актёр театра и кино, наиболее известный по своим ролям в лирических комедиях Эльдара Рязанова, включая «Иронию судьбы» и «Служебный роман».

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

Target predicate: актёр
Context triple: [Служебный роман, актёр, Андрей Мягков]

A. employedActor
Indicates that one entity has hired or currently employs another entity to perform work or services.
B. europeanFilmActor
Indicates that a person is an actor who performs in films produced in Europe or within the European film industry.
C. starredActor chosen
Indicates that an actor performed a leading or significant role in a particular production or work.
D. airedStarringActor
Indicates that a specific airing of a program featured a particular actor in a starring role.
E. cast
Indicates that an agent selects and assigns a person or thing to play a specific role or function in a production or context.
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_69f0bd42cf308190bb01b20bc5b7c2d0`	completed	April 28, 2026, 1:59 p.m.
NER	Named-entity recognition	`batch_69f66babf5e08190b8e1007546f3881a`	completed	May 2, 2026, 9:25 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a267e9c276881909e9b83efd97e145f`	completed	June 8, 2026, 8:34 a.m.
NEDg	Description generation	`batch_6a268282fad08190a2910d0526965dfc`	completed	June 8, 2026, 8:51 a.m.
NED2	Entity disambiguation (via description)	`batch_6a26867701108190b9ab9434ee82344e`	completed	June 8, 2026, 9:08 a.m.
PD	Predicate disambiguation	`batch_69f66339175c819080bd70f0ff7057b1`	completed	May 2, 2026, 8:48 p.m.

Created at: April 28, 2026, 3:57 p.m.