Triple

T3975263
Position Surface form Disambiguated ID Type / Status
Subject Shusha uezd E85623 entity
Predicate hasTown P847 FINISHED
Object Askeran
Askeran is a town in the disputed Nagorno-Karabakh region of the South Caucasus, historically known for its strategic location and fortress.
 E405042 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: Askeran | Statement: [Shusha uezd, hasTown, Askeran]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Askeran
Context triple: [Shusha uezd, hasTown, Askeran]
  • A. Asker
    Asker is a municipality in Viken county, Norway, known for its coastal location near Oslo and its mix of residential areas, cultural sites, and natural landscapes.
  • B. Andselv
    Andselv is a small Norwegian village located in the Troms region, known for its position along the Andselva river and proximity to Bardufoss.
  • C. Ashkun
    Ashkun is a Nuristani language spoken by the Ashkun people in parts of eastern Afghanistan.
  • D. Akure
    Akure is the capital city of Ondo State in southwestern Nigeria, known as an important administrative and commercial center in the region.
  • E. Solbo
    Solbo is a locality within Botkyrka Municipality in Stockholm County, Sweden.
  • 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: Askeran
Triple: [Shusha uezd, hasTown, Askeran]
Generated description
Askeran is a town in the disputed Nagorno-Karabakh region of the South Caucasus, historically known for its strategic location and fortress.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Askeran
Target entity description: Askeran is a town in the disputed Nagorno-Karabakh region of the South Caucasus, historically known for its strategic location and fortress.
  • A. Asker
    Asker is a municipality in Viken county, Norway, known for its coastal location near Oslo and its mix of residential areas, cultural sites, and natural landscapes.
  • B. Andselv
    Andselv is a small Norwegian village located in the Troms region, known for its position along the Andselva river and proximity to Bardufoss.
  • C. Ashkun
    Ashkun is a Nuristani language spoken by the Ashkun people in parts of eastern Afghanistan.
  • D. Akure
    Akure is the capital city of Ondo State in southwestern Nigeria, known as an important administrative and commercial center in the region.
  • E. Solbo
    Solbo is a locality within Botkyrka Municipality in Stockholm County, Sweden.
  • 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_69aed93908348190a26c8aaf4fab3e86 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aef9b511f88190afca12c77481b344 completed March 9, 2026, 4:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5401712188190aa6144dc1d5dcab6 completed March 14, 2026, 11:01 a.m.
NEDg Description generation batch_69b54411546481908627a8b3ce7a433a completed March 14, 2026, 11:18 a.m.
NED2 Entity disambiguation (via description) batch_69b544a02d5c8190a76a074cc7e98cc5 completed March 14, 2026, 11:21 a.m.
Created at: March 9, 2026, 3:33 p.m.