Triple

T12916658
Position Surface form Disambiguated ID Type / Status
Subject Razgrad Province E309002 entity
Predicate hasSettlement P1068 FINISHED
Object Zavet
Zavet is a small town and municipal center located in northeastern Bulgaria.
E1008939 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: Zavet | Statement: [Razgrad Province, hasSettlement, Zavet]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Zavet
Context triple: [Razgrad Province, hasSettlement, Zavet]
  • A. Pošeň
    Pošeň is a local neighborhood within the Ružinov borough of Bratislava, Slovakia.
  • B. Znamianka
    Znamianka is a city in central Ukraine that serves as an important regional railway junction and administrative center within Kirovohrad Oblast.
  • C. Nezvěstice
    Nezvěstice is a village and municipality in the Plzeň Region of the Czech Republic, known for its location in the Úslava River valley.
  • D. Zaosie
    Zaosie is a small village in present-day Belarus, best known as the birthplace of the Polish Romantic poet Adam Mickiewicz.
  • E. Kabale
    Kabale is a town in southwestern Uganda that serves as a key regional center and gateway to nearby attractions such as Bwindi Impenetrable National Park.
  • 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: Zavet
Triple: [Razgrad Province, hasSettlement, Zavet]
Generated description
Zavet is a small town and municipal center located in northeastern Bulgaria.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Zavet
Target entity description: Zavet is a small town and municipal center located in northeastern Bulgaria.
  • A. Pošeň
    Pošeň is a local neighborhood within the Ružinov borough of Bratislava, Slovakia.
  • B. Znamianka
    Znamianka is a city in central Ukraine that serves as an important regional railway junction and administrative center within Kirovohrad Oblast.
  • C. Nezvěstice
    Nezvěstice is a village and municipality in the Plzeň Region of the Czech Republic, known for its location in the Úslava River valley.
  • D. Zaosie
    Zaosie is a small village in present-day Belarus, best known as the birthplace of the Polish Romantic poet Adam Mickiewicz.
  • E. Kabale
    Kabale is a town in southwestern Uganda that serves as a key regional center and gateway to nearby attractions such as Bwindi Impenetrable National Park.
  • 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_69f6a77ba20081908f72f46f64382fca completed May 3, 2026, 1:40 a.m.
Created at: April 9, 2026, 5:41 p.m.