Triple

T1273890
Position Surface form Disambiguated ID Type / Status
Subject Kakheti E15768 entity
Predicate traditionalGrapeVariety P28269 FINISHED
Object Kisi
Kisi is an indigenous Georgian white grape variety from the Kakheti region, known for producing aromatic, full-bodied wines often made in traditional qvevri.
 E144382 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: Kisi | Statement: [Kakheti, traditionalGrapeVariety, Kisi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kisi
Context triple: [Kakheti, traditionalGrapeVariety, Kisi]
  • A. Koba
    Koba was a revolutionary alias used by Joseph Stalin during his early political activities in the Bolshevik movement.
  • B. Keda
    Keda is a small town and administrative center in the mountainous Adjara region of southwestern Georgia.
  • C. Kip
    Kip is a young Sikh British-Indian army sapper in Michael Ondaatje’s novel "The English Patient," whose expertise in bomb disposal and complex relationship with the other characters explore themes of war, identity, and colonialism.
  • D. Ku
    Ku is a principal Hawaiian god associated with war, politics, and prosperity, widely venerated in traditional Native Hawaiian religion.
  • E. Kali
    Kali is a fierce and powerful Hindu goddess associated with time, destruction, and the transformative power that annihilates evil.
  • 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: Kisi
Triple: [Kakheti, traditionalGrapeVariety, Kisi]
Generated description
Kisi is an indigenous Georgian white grape variety from the Kakheti region, known for producing aromatic, full-bodied wines often made in traditional qvevri.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kisi
Target entity description: Kisi is an indigenous Georgian white grape variety from the Kakheti region, known for producing aromatic, full-bodied wines often made in traditional qvevri.
  • A. Koba
    Koba was a revolutionary alias used by Joseph Stalin during his early political activities in the Bolshevik movement.
  • B. Keda
    Keda is a small town and administrative center in the mountainous Adjara region of southwestern Georgia.
  • C. Kip
    Kip is a young Sikh British-Indian army sapper in Michael Ondaatje’s novel "The English Patient," whose expertise in bomb disposal and complex relationship with the other characters explore themes of war, identity, and colonialism.
  • D. Ku
    Ku is a principal Hawaiian god associated with war, politics, and prosperity, widely venerated in traditional Native Hawaiian religion.
  • E. Kali
    Kali is a fierce and powerful Hindu goddess associated with time, destruction, and the transformative power that annihilates evil.
  • 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_69ac998e56488190ac3cf51563335e30 completed March 7, 2026, 9:33 p.m.
NEDg Description generation batch_69ac9a14a53481908c45e4e6609a368e completed March 7, 2026, 9:35 p.m.
NED2 Entity disambiguation (via description) batch_69ac9a98788881909e316322af87b848 completed March 7, 2026, 9:37 p.m.
Created at: March 1, 2026, 7:50 p.m.