Triple

T16351587
Position Surface form Disambiguated ID Type / Status
Subject Tusheti E397072 entity
Predicate hasVillage P4011 FINISHED
Object Shenako
Shenako is a remote mountain village in Georgia’s historic Tusheti region, known for its traditional stone architecture and preserved highland culture.
 E1208663 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: Shenako | Statement: [Tusheti, hasVillage, Shenako]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Shenako
Context triple: [Tusheti, hasVillage, Shenako]
  • A. Shenir
    Shenir is an alternate name for the Sinyar language, a Nilo-Saharan language spoken by the Sinyar people of western Sudan and eastern Chad.
  • B. Sraosha
    Sraosha is a key Zoroastrian divinity associated with obedience, religious devotion, and the protection of the righteous, often depicted as a guardian against evil forces.
  • C. Shinasha
    Shinasha is a North Omotic language spoken by the Shinasha people of western Ethiopia.
  • D. Shachi
    Shachi, also known as Indrani, is the queen of the gods and the goddess of beauty and prosperity in Hindu mythology, revered as the wife of the god Indra.
  • E. Sanchica
    Sanchica is the fictional daughter of Sancho Panza in Miguel de Cervantes' novel "Don Quixote."
  • 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: Shenako
Triple: [Tusheti, hasVillage, Shenako]
Generated description
Shenako is a remote mountain village in Georgia’s historic Tusheti region, known for its traditional stone architecture and preserved highland culture.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Shenako
Target entity description: Shenako is a remote mountain village in Georgia’s historic Tusheti region, known for its traditional stone architecture and preserved highland culture.
  • A. Shenir
    Shenir is an alternate name for the Sinyar language, a Nilo-Saharan language spoken by the Sinyar people of western Sudan and eastern Chad.
  • B. Sraosha
    Sraosha is a key Zoroastrian divinity associated with obedience, religious devotion, and the protection of the righteous, often depicted as a guardian against evil forces.
  • C. Shinasha
    Shinasha is a North Omotic language spoken by the Shinasha people of western Ethiopia.
  • D. Shachi
    Shachi, also known as Indrani, is the queen of the gods and the goddess of beauty and prosperity in Hindu mythology, revered as the wife of the god Indra.
  • E. Sanchica
    Sanchica is the fictional daughter of Sancho Panza in Miguel de Cervantes' novel "Don Quixote."
  • 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_69d87f26864c819088365ca381a003c2 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e2facbf60c8190aa47d4c45ff59354 completed April 18, 2026, 3:30 a.m.
NED1 Entity disambiguation (via context triple) batch_6a002db6375c81908c64dbe2bc987b1a completed May 10, 2026, 7:03 a.m.
NEDg Description generation batch_6a00304d7c888190a018d865eb51f0a0 completed May 10, 2026, 7:14 a.m.
NED2 Entity disambiguation (via description) batch_6a00309ceba88190a982b439a1e72e78 completed May 10, 2026, 7:15 a.m.
Created at: April 10, 2026, 5:07 a.m.