Triple

T23953046

Position	Surface form	Disambiguated ID	Type / Status
Subject	Шхара	`E603101`	entity
Predicate	расположенаВблизиНаселённогоПункта	`P61362`	FINISHED
Object	Ушгули Ушгули — это одно из самых высокогорных постоянно населённых селений в Европе, расположенное в регионе Сванетия в Грузии и известное своими средневековыми сванскими башнями и включением в список Всемирного наследия ЮНЕСКО.	`E1608173`	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: Ушгули | Statement: [Шхара, расположенаВблизиНаселённогоПункта, Ушгули]

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: Ушгули
Triple: [Шхара, расположенаВблизиНаселённогоПункта, Ушгули]

Generated description

Ушгули — это одно из самых высокогорных постоянно населённых селений в Европе, расположенное в регионе Сванетия в Грузии и известное своими средневековыми сванскими башнями и включением в список Всемирного наследия ЮНЕСКО.

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

Target predicate: расположенаВблизиНаселённогоПункта
Context triple: [Шхара, расположенаВблизиНаселённогоПункта, Ушгули]

A. расположенаНа
Indicates that one entity is located on the surface or area of another entity.
B. имеетНаселённыйПункт
Indicates that an entity possesses or includes a specific populated locality (such as a town, village, or city) within its structure or territory.
C. oftenLocatedNear
Indicates that one entity is frequently found in close physical proximity to another entity.
D. nearbyTo chosen
Indicates that one entity is located close in distance or position to another entity.
E. distanceFromNearestSettlementKilometers
Indicates the distance, measured in kilometers, from an entity’s location to the closest human settlement.
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_69e2953e4924819093f1c24c03476b42`	completed	April 17, 2026, 8:17 p.m.
NER	Named-entity recognition	`batch_69f1d0d558748190a51b5732a3e6713c`	completed	April 29, 2026, 9:35 a.m.
NED1	Entity disambiguation (via context triple)	`batch_6a0f76554dc88190a0448f4b707f9864`	completed	May 21, 2026, 9:17 p.m.
NEDg	Description generation	`batch_6a0f7763b168819096e38c871623606d`	completed	May 21, 2026, 9:21 p.m.
NED2	Entity disambiguation (via description)	`batch_6a0f78495eb481908d64e7caa0e065b4`	completed	May 21, 2026, 9:25 p.m.
PD	Predicate disambiguation	`batch_69f1615518088190a206f54e2fdb14a3`	completed	April 29, 2026, 1:39 a.m.

Created at: April 17, 2026, 9:21 p.m.