Triple

T16507214
Position Surface form Disambiguated ID Type / Status
Subject Struga region E400960 entity
Predicate hasRiver P165 FINISHED
Object Black Drim
Black Drim is a major river in the Balkans that flows from Lake Ohrid through North Macedonia and Albania before joining the White Drin to form the Drin River.
 E1217276 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: Black Drim | Statement: [Struga region, hasRiver, Black Drim]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Black Drim
Context triple: [Struga region, hasRiver, Black Drim]
  • A. Blacker
    Blacker is a comparative form of the color term "black," indicating a greater degree of darkness or blackness.
  • B. White Demon
    White Demon is a formidable mythical monster from the Persian epic Shahnameh, best known as the fearsome adversary slain by the hero Rostam.
  • C. Blinde Rot
    Blinde Rot is a river in Germany that serves as one of the tributaries feeding into the Kocher River.
  • D. The Crazed
    "The Crazed" is a novel by Chinese-American author Ha Jin that explores the psychological and political turmoil of post-Cultural Revolution China through a graduate student's relationship with his ailing mentor.
  • E. Black Regen
    Black Regen is a river in Bavaria, Germany, known as one of the main headstreams that form the Regen River.
  • 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: Black Drim
Triple: [Struga region, hasRiver, Black Drim]
Generated description
Black Drim is a major river in the Balkans that flows from Lake Ohrid through North Macedonia and Albania before joining the White Drin to form the Drin River.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Black Drim
Target entity description: Black Drim is a major river in the Balkans that flows from Lake Ohrid through North Macedonia and Albania before joining the White Drin to form the Drin River.
  • A. Blacker
    Blacker is a comparative form of the color term "black," indicating a greater degree of darkness or blackness.
  • B. White Demon
    White Demon is a formidable mythical monster from the Persian epic Shahnameh, best known as the fearsome adversary slain by the hero Rostam.
  • C. Blinde Rot
    Blinde Rot is a river in Germany that serves as one of the tributaries feeding into the Kocher River.
  • D. The Crazed
    "The Crazed" is a novel by Chinese-American author Ha Jin that explores the psychological and political turmoil of post-Cultural Revolution China through a graduate student's relationship with his ailing mentor.
  • E. Black Regen
    Black Regen is a river in Bavaria, Germany, known as one of the main headstreams that form the Regen River.
  • 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_69d88381f6148190819958a038be990e completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e32e536e5c8190bef31ab979d2880a completed April 18, 2026, 7:10 a.m.
NED1 Entity disambiguation (via context triple) batch_6a005832bcb48190a905ee7c9bff2c5b completed May 10, 2026, 10:04 a.m.
NEDg Description generation batch_6a0059126e588190b531c145f3c155b4 completed May 10, 2026, 10:08 a.m.
NED2 Entity disambiguation (via description) batch_6a0059b5a1f8819089caefc121246739 completed May 10, 2026, 10:11 a.m.
Created at: April 10, 2026, 5:14 a.m.