Triple

T29843863
Position Surface form Disambiguated ID Type / Status
Subject Aksakovo E757875 entity
Predicate partOf P40 FINISHED
Object Aksakovo Municipality
Aksakovo Municipality is an administrative region in northeastern Bulgaria that includes the town of Aksakovo and surrounding settlements within Varna Province.
E1893475 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: Aksakovo Municipality | Statement: [Aksakovo, partOf, Aksakovo Municipality]
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: Aksakovo Municipality
Triple: [Aksakovo, partOf, Aksakovo Municipality]
Generated description
Aksakovo Municipality is an administrative region in northeastern Bulgaria that includes the town of Aksakovo and surrounding settlements within Varna Province.

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_69f224593f6c81908785a560fe659f58 completed April 29, 2026, 3:31 p.m.
NER Named-entity recognition batch_69f6760bfa788190ad868de214807eba completed May 2, 2026, 10:09 p.m.
NED1 Entity disambiguation (via context triple) batch_6a2721dd963c8190a3501f3b113206fc completed June 8, 2026, 8:11 p.m.
NEDg Description generation batch_6a27227fc3508190a35d972c5f0f004d completed June 8, 2026, 8:13 p.m.
NED2 Entity disambiguation (via description) batch_6a272344de1c819093cc8b8387452668 completed June 8, 2026, 8:17 p.m.
Created at: April 29, 2026, 5:40 p.m.