Triple

T8771382
Position Surface form Disambiguated ID Type / Status
Subject Varna Province E208470 entity
Predicate hasMajorTown P316 FINISHED
Object Aksakovo
Aksakovo is a town in northeastern Bulgaria that serves as an important residential and industrial center near the city of Varna.
E757875 NE FINISHED

How this triple was built (4 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 | Statement: [Varna Province, hasMajorTown, Aksakovo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Aksakovo
Context triple: [Varna Province, hasMajorTown, Aksakovo]
  • A. Konakovo
    Konakovo is a town in Tver Oblast, Russia, situated on the Volga River and known for its power station and riverside recreation.
  • B. Petrovskoye
    Petrovskoye was the original Russian fortress settlement that later developed into the modern city of Makhachkala in Dagestan, Russia.
  • C. Orekhovo
    Orekhovo is a Moscow Metro station on the Zamoskvoretskaya Line serving the Orekhovo-Borisovo district in southern Moscow.
  • D. Feodorovsky Gorodok
    Feodorovsky Gorodok is a historic architectural complex in Pushkin, Russia, built in a neo-Russian style as a residence and military settlement associated with the last Russian imperial family.
  • E. Kuznetsovo
    Kuznetsovo is the former name of the town now known as Belogorsk in Russia’s Amur Oblast.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
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
Triple: [Varna Province, hasMajorTown, Aksakovo]
Generated description
Aksakovo is a town in northeastern Bulgaria that serves as an important residential and industrial center near the city of Varna.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Aksakovo
Target entity description: Aksakovo is a town in northeastern Bulgaria that serves as an important residential and industrial center near the city of Varna.
  • A. Konakovo
    Konakovo is a town in Tver Oblast, Russia, situated on the Volga River and known for its power station and riverside recreation.
  • B. Petrovskoye
    Petrovskoye was the original Russian fortress settlement that later developed into the modern city of Makhachkala in Dagestan, Russia.
  • C. Orekhovo
    Orekhovo is a Moscow Metro station on the Zamoskvoretskaya Line serving the Orekhovo-Borisovo district in southern Moscow.
  • D. Feodorovsky Gorodok
    Feodorovsky Gorodok is a historic architectural complex in Pushkin, Russia, built in a neo-Russian style as a residence and military settlement associated with the last Russian imperial family.
  • E. Kuznetsovo
    Kuznetsovo is the former name of the town now known as Belogorsk in Russia’s Amur Oblast.
  • F. None of above. chosen

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_69ca835edb4481909b4aafb616dc5eb7 completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc5f2b08f881909f3d4fab2eda1d67 completed March 31, 2026, 11:56 p.m.
NED1 Entity disambiguation (via context triple) batch_69cf51b7d05c8190b84e02a8796d3422 completed April 3, 2026, 5:35 a.m.
NEDg Description generation batch_69cf55016d108190b6de72787962564f completed April 3, 2026, 5:49 a.m.
NED2 Entity disambiguation (via description) batch_69cf55940918819088ed8a6ea2f8f460 completed April 3, 2026, 5:52 a.m.
Created at: March 30, 2026, 6:41 p.m.