Triple

T6918083
Position Surface form Disambiguated ID Type / Status
Subject Sulak River E160113 entity
Predicate hasTributary P415 FINISHED
Object Kara Koysu
Kara Koysu is a river in the North Caucasus region that serves as a significant tributary within the Sulak River basin.
 E629749 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: Kara Koysu | Statement: [Sulak River, hasTributary, Kara Koysu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kara Koysu
Context triple: [Sulak River, hasTributary, Kara Koysu]
  • A. Kagermeer
    Kagermeer is a lake in the Kagerplassen lake district in South Holland, Netherlands, popular for boating and watersports.
  • B. Karosta
    Karosta is a historic former military port district in the Latvian city of Liepāja, known for its Tsarist-era fortifications, Soviet naval heritage, and distinctive coastal landscape.
  • C. Kara
    Kara is a steel bracelet worn by Sikhs as a religious symbol of unity, restraint, and connection to the divine.
  • D. Uma
    Uma is an Austronesian language spoken primarily in Central Sulawesi, Indonesia.
  • E. Erna
    Erna is the given name of Erna Schneider Hoover, an American mathematician and pioneering computer scientist known for revolutionizing telephone switching systems.
  • 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: Kara Koysu
Triple: [Sulak River, hasTributary, Kara Koysu]
Generated description
Kara Koysu is a river in the North Caucasus region that serves as a significant tributary within the Sulak River basin.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kara Koysu
Target entity description: Kara Koysu is a river in the North Caucasus region that serves as a significant tributary within the Sulak River basin.
  • A. Kagermeer
    Kagermeer is a lake in the Kagerplassen lake district in South Holland, Netherlands, popular for boating and watersports.
  • B. Karosta
    Karosta is a historic former military port district in the Latvian city of Liepāja, known for its Tsarist-era fortifications, Soviet naval heritage, and distinctive coastal landscape.
  • C. Kara
    Kara is a steel bracelet worn by Sikhs as a religious symbol of unity, restraint, and connection to the divine.
  • D. Uma
    Uma is an Austronesian language spoken primarily in Central Sulawesi, Indonesia.
  • E. Erna
    Erna is the given name of Erna Schneider Hoover, an American mathematician and pioneering computer scientist known for revolutionizing telephone switching systems.
  • 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_69c6883ab1008190a07129ff06f625d9 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6d9e17ea08190b8c4142af8adfba0 completed March 27, 2026, 7:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7512b39b081908370c43ed3d65829 completed March 28, 2026, 3:55 a.m.
NEDg Description generation batch_69c7523737e48190b2ad3e7bea02878d completed March 28, 2026, 3:59 a.m.
NED2 Entity disambiguation (via description) batch_69c752eb3e1c8190bad35727e573c41f completed March 28, 2026, 4:02 a.m.
Created at: March 27, 2026, 2:26 p.m.