Triple

T14059771
Position Surface form Disambiguated ID Type / Status
Subject Heves County E338311 entity
Predicate knownFor P22 FINISHED
Object Egri Bikavér
Egri Bikavér is a historic Hungarian red wine blend, often called “Bull’s Blood,” renowned for its robust, spicy character and association with the Eger wine region.
 E1078696 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: Egri Bikavér | Statement: [Heves County, knownFor, Egri Bikavér]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Egri Bikavér
Context triple: [Heves County, knownFor, Egri Bikavér]
  • A. Eperjes
    Eperjes is a historic town in present-day Slovakia, known today as Prešov, which was one of the major urban centers of the former Upper Hungary region.
  • B. Bicske
    Bicske is a small town in central Hungary known for its historical significance and location along major transportation routes west of Budapest.
  • C. Mundruczó
    Mundruczó is the surname of Hungarian film and theatre director Kornél Mundruczó, known for his innovative and often provocative works.
  • D. Ercsi
    Ercsi is a small town in central Hungary situated along the Danube River in Fejér County.
  • E. Csokas
    Csokas is the surname of Marton Csokas, a New Zealand actor known for roles in films such as "The Lord of the Rings" and "Kingdom of Heaven."
  • 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: Egri Bikavér
Triple: [Heves County, knownFor, Egri Bikavér]
Generated description
Egri Bikavér is a historic Hungarian red wine blend, often called “Bull’s Blood,” renowned for its robust, spicy character and association with the Eger wine region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Egri Bikavér
Target entity description: Egri Bikavér is a historic Hungarian red wine blend, often called “Bull’s Blood,” renowned for its robust, spicy character and association with the Eger wine region.
  • A. Eperjes
    Eperjes is a historic town in present-day Slovakia, known today as Prešov, which was one of the major urban centers of the former Upper Hungary region.
  • B. Bicske
    Bicske is a small town in central Hungary known for its historical significance and location along major transportation routes west of Budapest.
  • C. Mundruczó
    Mundruczó is the surname of Hungarian film and theatre director Kornél Mundruczó, known for his innovative and often provocative works.
  • D. Ercsi
    Ercsi is a small town in central Hungary situated along the Danube River in Fejér County.
  • E. Csokas
    Csokas is the surname of Marton Csokas, a New Zealand actor known for roles in films such as "The Lord of the Rings" and "Kingdom of Heaven."
  • 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_69d81c67ba6c819091935650dfb3b895 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de5686f51c81908c33143ecbaae83d completed April 14, 2026, 3 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcb662c37c8190a629278a97060080 completed May 7, 2026, 3:57 p.m.
NEDg Description generation batch_69fcc99fca8c8190bbcafba5bacfdfda completed May 7, 2026, 5:19 p.m.
NED2 Entity disambiguation (via description) batch_69fcca3a375c819092b3f67612d2ec0c completed May 7, 2026, 5:22 p.m.
Created at: April 9, 2026, 10:21 p.m.