Triple

T3318703
Position Surface form Disambiguated ID Type / Status
Subject Lake Sevan E69740 entity
Predicate nearbySettlement P350 FINISHED
Object Vardenis
Vardenis is a town in eastern Armenia located near Lake Sevan, known as a local administrative and economic center in the Gegharkunik Province.
 E346655 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: Vardenis | Statement: [Lake Sevan, nearbySettlement, Vardenis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Vardenis
Context triple: [Lake Sevan, nearbySettlement, Vardenis]
  • A. Vardzia
    Vardzia is a medieval cave monastery complex in southern Georgia, renowned for its extensive rock-cut dwellings and frescoed church.
  • B. Linas
    Linas is a commune in the southern suburbs of Paris, located in the Essonne department of the Île-de-France region in northern France.
  • C. Agenais
    Agenais refers to the inhabitants or natives of Agen, a historic town in southwestern France.
  • D. Vara
    Vara is a short form of the female given name Varvara, commonly used in Slavic languages.
  • E. Palaite
    Palaite is an ancient Anatolian language, closely related to Hittite and Luwian, once spoken in the region of Pala in north-central Anatolia.
  • 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: Vardenis
Triple: [Lake Sevan, nearbySettlement, Vardenis]
Generated description
Vardenis is a town in eastern Armenia located near Lake Sevan, known as a local administrative and economic center in the Gegharkunik Province.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Vardenis
Target entity description: Vardenis is a town in eastern Armenia located near Lake Sevan, known as a local administrative and economic center in the Gegharkunik Province.
  • A. Vardzia
    Vardzia is a medieval cave monastery complex in southern Georgia, renowned for its extensive rock-cut dwellings and frescoed church.
  • B. Linas
    Linas is a commune in the southern suburbs of Paris, located in the Essonne department of the Île-de-France region in northern France.
  • C. Agenais
    Agenais refers to the inhabitants or natives of Agen, a historic town in southwestern France.
  • D. Vara
    Vara is a short form of the female given name Varvara, commonly used in Slavic languages.
  • E. Palaite
    Palaite is an ancient Anatolian language, closely related to Hittite and Luwian, once spoken in the region of Pala in north-central Anatolia.
  • 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_69ad85a0bb048190a5458d2738012d61 completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb1151f3c8190911af4edac701116 completed March 8, 2026, 5:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69b2f40055a48190afe401a488d3ae34 completed March 12, 2026, 5:12 p.m.
NEDg Description generation batch_69b2fa0ed27c8190a32c153b44b7b2dd completed March 12, 2026, 5:38 p.m.
NED2 Entity disambiguation (via description) batch_69b312b902fc819081ec01c3d418fae0 completed March 12, 2026, 7:23 p.m.
Created at: March 8, 2026, 3:11 p.m.