Triple

T12690303
Position Surface form Disambiguated ID Type / Status
Subject Seven Rila Lakes E303185 entity
Predicate hasLake P1025 FINISHED
Object Ribnoto ezero
Ribnoto ezero is one of Bulgaria’s famous Seven Rila Lakes, a high-altitude glacial lake in the Rila Mountains.
 E999014 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: Ribnoto ezero | Statement: [Seven Rila Lakes, hasLake, Ribnoto ezero]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Ribnoto ezero
Context triple: [Seven Rila Lakes, hasLake, Ribnoto ezero]
  • A. Iriba
    Iriba is a town in eastern Chad that serves as an important local center within the Wadi Fira region.
  • B. Černé jezero
    Černé jezero is the largest and deepest glacial lake in the Czech Republic, located in the Šumava Mountains near the German border.
  • C. Veliki Mokri Lug
    Veliki Mokri Lug is a suburban neighborhood and settlement on the outskirts of Belgrade, Serbia.
  • D. 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.
  • E. Sorpesee
    Sorpesee is a popular artificial lake in the Sauerland region of Germany, known for recreation, water sports, and scenic surroundings.
  • 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: Ribnoto ezero
Triple: [Seven Rila Lakes, hasLake, Ribnoto ezero]
Generated description
Ribnoto ezero is one of Bulgaria’s famous Seven Rila Lakes, a high-altitude glacial lake in the Rila Mountains.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Ribnoto ezero
Target entity description: Ribnoto ezero is one of Bulgaria’s famous Seven Rila Lakes, a high-altitude glacial lake in the Rila Mountains.
  • A. Iriba
    Iriba is a town in eastern Chad that serves as an important local center within the Wadi Fira region.
  • B. Černé jezero
    Černé jezero is the largest and deepest glacial lake in the Czech Republic, located in the Šumava Mountains near the German border.
  • C. Veliki Mokri Lug
    Veliki Mokri Lug is a suburban neighborhood and settlement on the outskirts of Belgrade, Serbia.
  • D. 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.
  • E. Sorpesee
    Sorpesee is a popular artificial lake in the Sauerland region of Germany, known for recreation, water sports, and scenic surroundings.
  • 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_69d7bdef90d48190b46b88270e780946 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d961dabb38819087738361f9de8066 completed April 10, 2026, 8:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69f671aacfa8819088fd113474638238 completed May 2, 2026, 9:50 p.m.
NEDg Description generation batch_69f6751f79148190a1735abf489fd106 completed May 2, 2026, 10:05 p.m.
NED2 Entity disambiguation (via description) batch_69f675c42fec8190b60751c0db88f3b6 completed May 2, 2026, 10:08 p.m.
Created at: April 9, 2026, 5:22 p.m.