Triple

T777210
Position Surface form Disambiguated ID Type / Status
Subject Imereti E16413 entity
Predicate hasCity P316 FINISHED
Object Vani
Vani is a historic town in western Georgia’s Imereti region, known for its important archaeological sites from the ancient Colchian civilization.
 E93383 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: Vani | Statement: [Imereti, hasCity, Vani]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Vani
Context triple: [Imereti, hasCity, Vani]
  • A. Pranhita
    Pranhita is a major river in central India that flows through the states of Maharashtra and Telangana before joining the Godavari River.
  • B. Yoogali
    Yoogali is a small town in the Riverina region of New South Wales, Australia, known for its agricultural surroundings and proximity to the city of Griffith.
  • C. Ponna
    Ponna was a prominent 10th-century Kannada poet of the Rashtrakuta court, renowned for his Jain devotional and classical literary works.
  • D. Sibi
    Sibi is a historic town and district in the Balochistan region of Pakistan, known for its hot climate and traditional annual cattle and horse fair.
  • E. Yerrapragada
    Yerrapragada was a prominent medieval Telugu poet and scholar, renowned for his contributions to classical Telugu literature and refinement of earlier works.
  • 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: Vani
Triple: [Imereti, hasCity, Vani]
Generated description
Vani is a historic town in western Georgia’s Imereti region, known for its important archaeological sites from the ancient Colchian civilization.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Vani
Target entity description: Vani is a historic town in western Georgia’s Imereti region, known for its important archaeological sites from the ancient Colchian civilization.
  • A. Pranhita
    Pranhita is a major river in central India that flows through the states of Maharashtra and Telangana before joining the Godavari River.
  • B. Yoogali
    Yoogali is a small town in the Riverina region of New South Wales, Australia, known for its agricultural surroundings and proximity to the city of Griffith.
  • C. Ponna
    Ponna was a prominent 10th-century Kannada poet of the Rashtrakuta court, renowned for his Jain devotional and classical literary works.
  • D. Sibi
    Sibi is a historic town and district in the Balochistan region of Pakistan, known for its hot climate and traditional annual cattle and horse fair.
  • E. Yerrapragada
    Yerrapragada was a prominent medieval Telugu poet and scholar, renowned for his contributions to classical Telugu literature and refinement of earlier works.
  • 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_69a4936ad1fc81908f190208059ccf78 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a74da7648190adfad56717d564df completed March 1, 2026, 8:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69a6787ccafc8190a8d31089f906404b completed March 3, 2026, 5:58 a.m.
NEDg Description generation batch_69a678e7922881909fb8044658ce7865 completed March 3, 2026, 6 a.m.
NED2 Entity disambiguation (via description) batch_69a6794a539081908964bbcb2ad04391 completed March 3, 2026, 6:01 a.m.
Created at: March 1, 2026, 7:37 p.m.