Triple

T6909984
Position Surface form Disambiguated ID Type / Status
Subject Bulgarian cuisine E159905 entity
Predicate typicalDish P19483 FINISHED
Object kyufte
Kyufte is a traditional Bulgarian grilled meatball made from seasoned minced meat, often served with salads, bread, and yogurt-based sauces.
 E628011 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: kyufte | Statement: [Bulgarian cuisine, typicalDish, kyufte]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: kyufte
Context triple: [Bulgarian cuisine, typicalDish, kyufte]
  • A. Kaikesi
    Kaikesi is a figure in the Hindu epic Ramayana, known as the rakshasi queen of Lanka and the mother of Ravana, Kumbhakarna, and Vibhishana.
  • B. Koki
    Koki is a fictional character associated with Raka, likely appearing alongside them in a shared narrative or story.
  • C. Quorn
    Quorn is a village in Leicestershire, England, known for its historic charm and proximity to the River Soar and the Great Central Railway.
  • D. Kysset
    Kysset is the original Norwegian title of Edvard Munch’s painting "The Kiss," a symbolist work depicting an intimate, merging embrace between two lovers.
  • E. KAF
    KAF is the Kenya Air Force, the aerial warfare branch of the Kenya Defence Forces responsible for defending Kenyan airspace and providing air support to military operations.
  • 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: kyufte
Triple: [Bulgarian cuisine, typicalDish, kyufte]
Generated description
Kyufte is a traditional Bulgarian grilled meatball made from seasoned minced meat, often served with salads, bread, and yogurt-based sauces.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: kyufte
Target entity description: Kyufte is a traditional Bulgarian grilled meatball made from seasoned minced meat, often served with salads, bread, and yogurt-based sauces.
  • A. Kaikesi
    Kaikesi is a figure in the Hindu epic Ramayana, known as the rakshasi queen of Lanka and the mother of Ravana, Kumbhakarna, and Vibhishana.
  • B. Koki
    Koki is a fictional character associated with Raka, likely appearing alongside them in a shared narrative or story.
  • C. Quorn
    Quorn is a village in Leicestershire, England, known for its historic charm and proximity to the River Soar and the Great Central Railway.
  • D. Kysset
    Kysset is the original Norwegian title of Edvard Munch’s painting "The Kiss," a symbolist work depicting an intimate, merging embrace between two lovers.
  • E. KAF
    KAF is the Kenya Air Force, the aerial warfare branch of the Kenya Defence Forces responsible for defending Kenyan airspace and providing air support to military operations.
  • 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_69c68839ccb88190b4aa5cc1aca3448f completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6d9c00e948190b103a2b2a2738bb1 completed March 27, 2026, 7:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69c749076f6c819088b0b40dd3e208b0 completed March 28, 2026, 3:20 a.m.
NEDg Description generation batch_69c74c274258819099913ac5610730ac completed March 28, 2026, 3:33 a.m.
NED2 Entity disambiguation (via description) batch_69c74cca47b88190867550802db43ef0 completed March 28, 2026, 3:36 a.m.
Created at: March 27, 2026, 2:25 p.m.