Triple

T3556043
Position Surface form Disambiguated ID Type / Status
Subject Sava E75220 entity
Predicate majorTributary P415 FINISHED
Object Kupa
Kupa is a river in Central Europe that flows through Croatia and Slovenia before joining the Sava River.
E366528 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: Kupa | Statement: [Sava, majorTributary, Kupa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kupa
Context triple: [Sava, majorTributary, Kupa]
  • A. Bassein
    Bassein is a historic coastal town in western India, now known as Vasai, notable for its strategic port and colonial-era fortifications that played a key role in regional power struggles.
  • B. Dravinja
    Dravinja is a river in northeastern Slovenia that flows through the Dravinja Valley before joining the Drava River.
  • C. Morava
    Morava is a Central European river that forms part of the border between Austria, the Czech Republic, and Slovakia before joining the Danube near Bratislava.
  • D. Tribeni
    Tribeni is a town in West Bengal, India, historically known as a sacred confluence point of rivers and an important riverside settlement.
  • E. Nidzica
    Nidzica is a historic town in northern Poland known for its well-preserved medieval Teutonic castle and picturesque 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: Kupa
Triple: [Sava, majorTributary, Kupa]
Generated description
Kupa is a river in Central Europe that flows through Croatia and Slovenia before joining the Sava River.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kupa
Target entity description: Kupa is a river in Central Europe that flows through Croatia and Slovenia before joining the Sava River.
  • A. Bassein
    Bassein is a historic coastal town in western India, now known as Vasai, notable for its strategic port and colonial-era fortifications that played a key role in regional power struggles.
  • B. Dravinja
    Dravinja is a river in northeastern Slovenia that flows through the Dravinja Valley before joining the Drava River.
  • C. Morava
    Morava is a Central European river that forms part of the border between Austria, the Czech Republic, and Slovakia before joining the Danube near Bratislava.
  • D. Tribeni
    Tribeni is a town in West Bengal, India, historically known as a sacred confluence point of rivers and an important riverside settlement.
  • E. Nidzica
    Nidzica is a historic town in northern Poland known for its well-preserved medieval Teutonic castle and picturesque 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_69ad85d45090819086f34fb85d850a1e completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc0569fbc81909b855b6990c1415b completed March 8, 2026, 6:30 p.m.
NED1 Entity disambiguation (via context triple) batch_69b38bf40dac8190837053dd315303af completed March 13, 2026, 4 a.m.
NEDg Description generation batch_69b38c6e70a88190805de417a8740d64 completed March 13, 2026, 4:02 a.m.
NED2 Entity disambiguation (via description) batch_69b38cd2c540819083d3188c2dea7283 completed March 13, 2026, 4:04 a.m.
Created at: March 8, 2026, 3:20 p.m.