Triple

T12916657
Position Surface form Disambiguated ID Type / Status
Subject Razgrad Province E309002 entity
Predicate hasSettlement P1068 FINISHED
Object Kubrat
Kubrat is a small town in northeastern Bulgaria that serves as an administrative and economic center within Razgrad Province.
E1008672 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: Kubrat | Statement: [Razgrad Province, hasSettlement, Kubrat]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kubrat
Context triple: [Razgrad Province, hasSettlement, Kubrat]
  • A. Kubrat
    Kubrat was a 7th-century Bulgar ruler who founded Old Great Bulgaria and laid the foundations for the later Bulgarian state.
  • B. Yordan
    Yordan is a Cuban-born professional baseball player best known as a power-hitting outfielder and designated hitter for the Houston Astros in Major League Baseball.
  • C. Sredets
    Sredets is a small town and municipal center in southeastern Bulgaria known for its proximity to the city of Burgas and the Strandzha mountain region.
  • D. Korab
    Korab is a towering mountain on the border of Albania and North Macedonia, known as the highest peak of both countries and a prominent summit in the Balkan region.
  • E. Golyam Rezen
    Golyam Rezen is one of the prominent peaks of Bulgaria’s Vitosha Mountain, known for its alpine terrain and panoramic views over Sofia.
  • 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: Kubrat
Triple: [Razgrad Province, hasSettlement, Kubrat]
Generated description
Kubrat is a small town in northeastern Bulgaria that serves as an administrative and economic center within Razgrad Province.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kubrat
Target entity description: Kubrat is a small town in northeastern Bulgaria that serves as an administrative and economic center within Razgrad Province.
  • A. Kubrat
    Kubrat was a 7th-century Bulgar ruler who founded Old Great Bulgaria and laid the foundations for the later Bulgarian state.
  • B. Yordan
    Yordan is a Cuban-born professional baseball player best known as a power-hitting outfielder and designated hitter for the Houston Astros in Major League Baseball.
  • C. Sredets
    Sredets is a small town and municipal center in southeastern Bulgaria known for its proximity to the city of Burgas and the Strandzha mountain region.
  • D. Korab
    Korab is a towering mountain on the border of Albania and North Macedonia, known as the highest peak of both countries and a prominent summit in the Balkan region.
  • E. Golyam Rezen
    Golyam Rezen is one of the prominent peaks of Bulgaria’s Vitosha Mountain, known for its alpine terrain and panoramic views over Sofia.
  • 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_69d7bdf92b588190acdf2a2291ac4590 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d971a1e8088190af697629baecf59f completed April 10, 2026, 9:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6a571a3e48190a32d362adc6eaee2 completed May 3, 2026, 1:31 a.m.
NEDg Description generation batch_69f6a66cd21081909283d70e0f5d06cb completed May 3, 2026, 1:35 a.m.
NED2 Entity disambiguation (via description) batch_69f6a7792f948190bb0b324bee0cd8ac completed May 3, 2026, 1:40 a.m.
Created at: April 9, 2026, 5:41 p.m.