Triple

T11161903
Position Surface form Disambiguated ID Type / Status
Subject Yantra River E264055 entity
Predicate nearbySettlement P350 FINISHED
Object Kilifarevo
Kilifarevo is a small town in central northern Bulgaria, known for its historic monastery and picturesque setting in the Balkan foothills.
E909252 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: Kilifarevo | Statement: [Yantra River, nearbySettlement, Kilifarevo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kilifarevo
Context triple: [Yantra River, nearbySettlement, Kilifarevo]
  • A. Milevsko
    Milevsko is a small historic town in the Czech Republic known for its medieval monastery and location in the South Bohemian Region.
  • B. Kumluova
    Kumluova is a modern settlement in southwestern Turkey located close to the ancient Lycian sanctuary of Letoon.
  • C. Vidnoye
    Vidnoye is a small town in Moscow Oblast, Russia, functioning largely as a residential and industrial satellite of Moscow.
  • D. Uvarovo
    Uvarovo is a rural village located within the Gagarinsky District of Smolensk Oblast in western Russia.
  • E. Zakopianka
    Zakopianka is a major Polish road corridor connecting Kraków with the mountain resort town of Zakopane, serving as a primary route to the Tatra Mountains.
  • 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: Kilifarevo
Triple: [Yantra River, nearbySettlement, Kilifarevo]
Generated description
Kilifarevo is a small town in central northern Bulgaria, known for its historic monastery and picturesque setting in the Balkan foothills.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kilifarevo
Target entity description: Kilifarevo is a small town in central northern Bulgaria, known for its historic monastery and picturesque setting in the Balkan foothills.
  • A. Milevsko
    Milevsko is a small historic town in the Czech Republic known for its medieval monastery and location in the South Bohemian Region.
  • B. Kumluova
    Kumluova is a modern settlement in southwestern Turkey located close to the ancient Lycian sanctuary of Letoon.
  • C. Vidnoye
    Vidnoye is a small town in Moscow Oblast, Russia, functioning largely as a residential and industrial satellite of Moscow.
  • D. Uvarovo
    Uvarovo is a rural village located within the Gagarinsky District of Smolensk Oblast in western Russia.
  • E. Zakopianka
    Zakopianka is a major Polish road corridor connecting Kraków with the mountain resort town of Zakopane, serving as a primary route to the Tatra Mountains.
  • 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_69d6aa9ccddc8190868998c8b7beb060 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7e8832fe88190a74d81f9ed547baa completed April 9, 2026, 5:57 p.m.
NED1 Entity disambiguation (via context triple) batch_69e46375c61c8190939401f790cf1593 completed April 19, 2026, 5:09 a.m.
NEDg Description generation batch_69e46c374ca08190a876ee68dea9b821 completed April 19, 2026, 5:46 a.m.
NED2 Entity disambiguation (via description) batch_69e4747bc02c81908f0782cf85667f3f completed April 19, 2026, 6:21 a.m.
Created at: April 8, 2026, 9:29 p.m.