Triple

T3975264
Position Surface form Disambiguated ID Type / Status
Subject Shusha uezd E85623 entity
Predicate hasTown P847 FINISHED
Object Hadrut
Hadrut is a town in the Nagorno-Karabakh region, historically part of the Shusha uezd, known for its strategic location and role in regional conflicts between Armenia and Azerbaijan.
 E406722 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: Hadrut | Statement: [Shusha uezd, hasTown, Hadrut]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Hadrut
Context triple: [Shusha uezd, hasTown, Hadrut]
  • A. Berbera
    Berbera is a major port city on the Gulf of Aden in Somaliland, serving as a key maritime hub for trade in the Horn of Africa.
  • B. Hamra
    Hamra is a vibrant, cosmopolitan neighborhood in Beirut, Lebanon, known for its bustling commercial streets, cafes, and cultural life.
  • C. Ḍogrī
    Ḍogrī is the native name of the Dogri language, an Indo-Aryan language spoken primarily in the Jammu region of India.
  • D. Zgharta
    Zgharta is a town in northern Lebanon known as a predominantly Maronite Christian community and a local center for the surrounding Zgharta District.
  • E. Jowhar
    Jowhar is a town in southern Somalia that serves as the capital of the Middle Shabelle region and an important agricultural and administrative center.
  • 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: Hadrut
Triple: [Shusha uezd, hasTown, Hadrut]
Generated description
Hadrut is a town in the Nagorno-Karabakh region, historically part of the Shusha uezd, known for its strategic location and role in regional conflicts between Armenia and Azerbaijan.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Hadrut
Target entity description: Hadrut is a town in the Nagorno-Karabakh region, historically part of the Shusha uezd, known for its strategic location and role in regional conflicts between Armenia and Azerbaijan.
  • A. Berbera
    Berbera is a major port city on the Gulf of Aden in Somaliland, serving as a key maritime hub for trade in the Horn of Africa.
  • B. Hamra
    Hamra is a vibrant, cosmopolitan neighborhood in Beirut, Lebanon, known for its bustling commercial streets, cafes, and cultural life.
  • C. Ḍogrī
    Ḍogrī is the native name of the Dogri language, an Indo-Aryan language spoken primarily in the Jammu region of India.
  • D. Zgharta
    Zgharta is a town in northern Lebanon known as a predominantly Maronite Christian community and a local center for the surrounding Zgharta District.
  • E. Jowhar
    Jowhar is a town in southern Somalia that serves as the capital of the Middle Shabelle region and an important agricultural and administrative center.
  • 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_69b54c472d048190843b29a6a9a4be86 completed March 14, 2026, 11:53 a.m.
NEDg Description generation batch_69b54cd044f48190870ecc7c33cd3908 completed March 14, 2026, 11:56 a.m.
NED2 Entity disambiguation (via description) batch_69b54d5fa6c4819089d190c4cfdb8cd0 completed March 14, 2026, 11:58 a.m.
Created at: March 9, 2026, 3:33 p.m.