Triple

T35971059

Position	Surface form	Disambiguated ID	Type / Status
Subject	Изборская крепость	`E1040285`	entity
Predicate	имеетАльтернативноеНазвание	`P143838`	FINISHED
Object	Старый Изборск Старый Изборск — это один из древнейших русских городов-крепостей в Псковской области, известный хорошо сохранившейся Изборской крепостью и богатым историко-культурным наследием.	`E2163508`	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: Старый Изборск | Statement: [Изборская крепость, имеетАльтернативноеНазвание, Старый Изборск]

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: Старый Изборск
Triple: [Изборская крепость, имеетАльтернативноеНазвание, Старый Изборск]

Generated description

Старый Изборск — это один из древнейших русских городов-крепостей в Псковской области, известный хорошо сохранившейся Изборской крепостью и богатым историко-культурным наследием.

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

Target predicate: имеетАльтернативноеНазвание
Context triple: [Изборская крепость, имеетАльтернативноеНазвание, Старый Изборск]

A. haveAlternativeTitle
Indicates that an entity is known by one or more alternative titles or names in addition to its primary title.
B. hasAlternativeTitleCombination
Indicates that an entity is associated with one or more alternative titles considered together as a specific combination or set.
C. hasAlternativeFamilyName
Indicates that an entity is associated with an additional or variant family name besides its primary family name.
D. hasAlternativeToponymy chosen
Indicates that an entity is associated with one or more alternative place names or toponyms used to refer to the same geographic location.
E. hasTitleHolderAlternativeName
Indicates that an entity serving as a title holder is known by an alternative or additional name.
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_69f76e27758c81909b711cf38a130aaf`	completed	May 3, 2026, 3:47 p.m.
NER	Named-entity recognition	`batch_69fb3425666081908916fcbf3b5dd907`	completed	May 6, 2026, 12:29 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a38b7104e808190aa351f30e9eb2cb7`	completed	June 22, 2026, 4:16 a.m.
NEDg	Description generation	`batch_6a38b85bf4908190aecf55c46230322b`	completed	June 22, 2026, 4:21 a.m.
NED2	Entity disambiguation (via description)	`batch_6a38b8dae4ac8190a020a5e984acef6b`	completed	June 22, 2026, 4:23 a.m.
PD	Predicate disambiguation	`batch_69fb2f5f3164819099429c2cc3d24e01`	completed	May 6, 2026, 12:09 p.m.

Created at: May 3, 2026, 4:07 p.m.