Triple

T1273884
Position Surface form Disambiguated ID Type / Status
Subject Kakheti E15768 entity
Predicate hasWineAppellation P6176 FINISHED
Object Akhasheni
Akhasheni is a Georgian red wine appellation from the Kakheti region, known for its naturally semi-sweet wines made primarily from Saperavi grapes.
 E148499 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: Akhasheni | Statement: [Kakheti, hasWineAppellation, Akhasheni]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Akhasheni
Context triple: [Kakheti, hasWineAppellation, Akhasheni]
  • A. Akrosh
    Akrosh is an Indian film best known as a hard-hitting social drama written by acclaimed playwright and screenwriter Vijay Tendulkar.
  • B. Khashuri
    Khashuri is a town in central Georgia that serves as an important regional transport hub and gateway between eastern and western parts of the country.
  • C. Abasha
    Abasha is a small town in western Georgia’s Samegrelo region, known as a local administrative and cultural center.
  • D. Ihnasya
    Ihnasya is a city in Egypt known for its location within the Beni Suef Governorate along the Nile Valley.
  • E. Vostanik
    Vostanik is the birth name of Arshile Gorky, the influential Armenian-American painter associated with Abstract Expressionism.
  • 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: Akhasheni
Triple: [Kakheti, hasWineAppellation, Akhasheni]
Generated description
Akhasheni is a Georgian red wine appellation from the Kakheti region, known for its naturally semi-sweet wines made primarily from Saperavi grapes.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Akhasheni
Target entity description: Akhasheni is a Georgian red wine appellation from the Kakheti region, known for its naturally semi-sweet wines made primarily from Saperavi grapes.
  • A. Akrosh
    Akrosh is an Indian film best known as a hard-hitting social drama written by acclaimed playwright and screenwriter Vijay Tendulkar.
  • B. Khashuri
    Khashuri is a town in central Georgia that serves as an important regional transport hub and gateway between eastern and western parts of the country.
  • C. Abasha
    Abasha is a small town in western Georgia’s Samegrelo region, known as a local administrative and cultural center.
  • D. Ihnasya
    Ihnasya is a city in Egypt known for its location within the Beni Suef Governorate along the Nile Valley.
  • E. Vostanik
    Vostanik is the birth name of Arshile Gorky, the influential Armenian-American painter associated with Abstract Expressionism.
  • 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_69a4935a94308190bb92555b79032824 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4c48bec548190b25d4a74b323cc1b completed March 1, 2026, 10:58 p.m.
NED1 Entity disambiguation (via context triple) batch_69acb2fd091081908f4a60d7ce300c90 completed March 7, 2026, 11:21 p.m.
NEDg Description generation batch_69acb364f2d88190b20ad87001349562 completed March 7, 2026, 11:23 p.m.
NED2 Entity disambiguation (via description) batch_69acb3ce7720819095558536e0a978b8 completed March 7, 2026, 11:25 p.m.
Created at: March 1, 2026, 7:50 p.m.