Triple

T413265
Position Surface form Disambiguated ID Type / Status
Subject Khyber Pakhtunkhwa E9536 entity
Predicate hasCity P316 FINISHED
Object Kohat
Kohat is a historic city in northwestern Pakistan known for its strategic location, military cantonment, and role as a regional administrative and commercial center.
 E55857 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: Kohat | Statement: [Khyber Pakhtunkhwa, hasCity, Kohat]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kohat
Context triple: [Khyber Pakhtunkhwa, hasCity, Kohat]
  • A. Kawki
    Kawki is an indigenous Andean language closely related to Aymara and spoken by a small number of people in Peru.
  • B. Kutaisi
    Kutaisi is one of Georgia’s major cities, historically significant and formerly a capital, located in the western part of the country.
  • C. Kitchawan
    Kitchawan is a small hamlet within the town of Yorktown in Westchester County, New York, known for its residential character and proximity to natural areas.
  • D. Kykuit
    Kykuit is a historic Rockefeller family estate and grand mansion known for its architecture, art collections, and landscaped gardens overlooking the Hudson River in New York.
  • E. Kundagannada
    Kundagannada is a regional dialect of the Kannada language spoken primarily in the coastal districts of Karnataka, India.
  • 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: Kohat
Triple: [Khyber Pakhtunkhwa, hasCity, Kohat]
Generated description
Kohat is a historic city in northwestern Pakistan known for its strategic location, military cantonment, and role as a regional administrative and commercial center.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kohat
Target entity description: Kohat is a historic city in northwestern Pakistan known for its strategic location, military cantonment, and role as a regional administrative and commercial center.
  • A. Kawki
    Kawki is an indigenous Andean language closely related to Aymara and spoken by a small number of people in Peru.
  • B. Kutaisi
    Kutaisi is one of Georgia’s major cities, historically significant and formerly a capital, located in the western part of the country.
  • C. Kitchawan
    Kitchawan is a small hamlet within the town of Yorktown in Westchester County, New York, known for its residential character and proximity to natural areas.
  • D. Kykuit
    Kykuit is a historic Rockefeller family estate and grand mansion known for its architecture, art collections, and landscaped gardens overlooking the Hudson River in New York.
  • E. Kundagannada
    Kundagannada is a regional dialect of the Kannada language spoken primarily in the coastal districts of Karnataka, India.
  • 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_69a2e80111fc8190961d5b7c6154123f completed Feb. 28, 2026, 1:05 p.m.
NER Named-entity recognition batch_69a2ecdc422881908910428fd1aee7c6 completed Feb. 28, 2026, 1:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69a43e6cf1048190abf3f13ba35a3980 completed March 1, 2026, 1:26 p.m.
NEDg Description generation batch_69a43f00f8308190bd3534d3c3fde4cf completed March 1, 2026, 1:28 p.m.
NED2 Entity disambiguation (via description) batch_69a440e991408190a2b26a552fec32a8 completed March 1, 2026, 1:36 p.m.
Created at: Feb. 28, 2026, 1:09 p.m.