Triple

T8833650
Position Surface form Disambiguated ID Type / Status
Subject Sozh E210207 entity
Predicate hasTributary P415 FINISHED
Object Pronia
Pronia is a river that serves as a tributary of the Sozh River in Eastern Europe.
 E760035 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: Pronia | Statement: [Sozh, hasTributary, Pronia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Pronia
Context triple: [Sozh, hasTributary, Pronia]
  • A. Dagmária
    Dagmária is a feminine given name, a variant of the name Dagmar used in certain languages or cultures.
  • B. Almirena
    Almirena is a central soprano role in George Frideric Handel’s opera "Rinaldo," portrayed as the virtuous and beloved daughter of the Christian leader Goffredo.
  • C. Monarcha
    Monarcha is a genus of small insectivorous passerine birds commonly known as monarch flycatchers, found mainly in Australasia and the Pacific islands.
  • D. Basilia
    Basilia is a feminine given name derived from the male name Basil, often associated with Greek origins meaning "royal" or "kingly."
  • E. Basilissa Ouranon
    Basilissa Ouranon is the Greek name for the Queen of Heaven, a revered celestial goddess figure associated with divine authority and the heavens.
  • 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: Pronia
Triple: [Sozh, hasTributary, Pronia]
Generated description
Pronia is a river that serves as a tributary of the Sozh River in Eastern Europe.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Pronia
Target entity description: Pronia is a river that serves as a tributary of the Sozh River in Eastern Europe.
  • A. Dagmária
    Dagmária is a feminine given name, a variant of the name Dagmar used in certain languages or cultures.
  • B. Almirena
    Almirena is a central soprano role in George Frideric Handel’s opera "Rinaldo," portrayed as the virtuous and beloved daughter of the Christian leader Goffredo.
  • C. Monarcha
    Monarcha is a genus of small insectivorous passerine birds commonly known as monarch flycatchers, found mainly in Australasia and the Pacific islands.
  • D. Basilia
    Basilia is a feminine given name derived from the male name Basil, often associated with Greek origins meaning "royal" or "kingly."
  • E. Basilissa Ouranon
    Basilissa Ouranon is the Greek name for the Queen of Heaven, a revered celestial goddess figure associated with divine authority and the heavens.
  • 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_69ca8388549c819095fd94eadefbb007 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc60670fa48190b2a873f6498de7f6 completed April 1, 2026, 12:01 a.m.
NED1 Entity disambiguation (via context triple) batch_69cf8975a6f481908ee435d0435c8ffb completed April 3, 2026, 9:33 a.m.
NEDg Description generation batch_69cf8a8e5db0819080e6fdc3d8322e94 completed April 3, 2026, 9:38 a.m.
NED2 Entity disambiguation (via description) batch_69cf8b8849ec8190915fa087b1b46c18 completed April 3, 2026, 9:42 a.m.
Created at: March 30, 2026, 6:47 p.m.