Triple

T25599337

Position	Surface form	Disambiguated ID	Type / Status
Subject	City Garden of Sofia	`E641742`	entity
Predicate	near	`P350`	FINISHED
Object	Tsar Osvoboditel Boulevard Tsar Osvoboditel Boulevard is a major central thoroughfare in Sofia, Bulgaria, known for its historic buildings, governmental institutions, and cultural landmarks.	`E1736615`	NE FINISHED

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: Tsar Osvoboditel Boulevard | Statement: [City Garden of Sofia, near, Tsar Osvoboditel Boulevard]

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: Tsar Osvoboditel Boulevard
Triple: [City Garden of Sofia, near, Tsar Osvoboditel Boulevard]

Generated description

Tsar Osvoboditel Boulevard is a major central thoroughfare in Sofia, Bulgaria, known for its historic buildings, governmental institutions, and cultural landmarks.

Provenance (5 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_69e75dc60d108190b7e2419e36b0134b`	completed	April 21, 2026, 11:21 a.m.
NER	Named-entity recognition	`batch_69f5f9a53aa48190b935de0228cb5be3`	completed	May 2, 2026, 1:18 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a11fe429e888190b9b3f75242879c47`	completed	May 23, 2026, 7:21 p.m.
NEDg	Description generation	`batch_6a11fed8fd9881908e6822bc418066e6`	completed	May 23, 2026, 7:24 p.m.
NED2	Entity disambiguation (via description)	`batch_6a11ff33e3448190996da2faf6f3f6b5`	completed	May 23, 2026, 7:25 p.m.

Created at: April 21, 2026, 4:30 p.m.