Triple

T16768229
Position Surface form Disambiguated ID Type / Status
Subject Rio São Francisco E407523 entity
Predicate majorTributary P415 FINISHED
Object Rio Corrente
Rio Corrente is a significant river in Brazil that serves as one of the important tributaries feeding the São Francisco River system.
 E1368495 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: Rio Corrente | Statement: [Rio São Francisco, majorTributary, Rio Corrente]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Rio Corrente
Context triple: [Rio São Francisco, majorTributary, Rio Corrente]
  • A. Rio Côa
    Rio Côa is a river in northeastern Portugal known for flowing through the Côa Valley, an area famous for its prehistoric open-air rock art sites.
  • B. Mundo River
    The Mundo River is a watercourse in southeastern Spain known for its scenic source at the Riópar waterfalls and for feeding into the Segura River.
  • C. Marta River
    The Marta River is a watercourse in central Italy that drains Lake Bolsena and flows southwest toward the Tyrrhenian Sea.
  • D. Rio Corgo
    Rio Corgo is a river in northern Portugal that flows through the Trás-os-Montes region before joining the Douro River.
  • E. Rio Soberbo
    Rio Soberbo is a river in the state of Rio de Janeiro, Brazil, known for flowing through the municipality of Guapimirim in the Serra dos Órgãos region.
  • 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: Rio Corrente
Triple: [Rio São Francisco, majorTributary, Rio Corrente]
Generated description
Rio Corrente is a significant river in Brazil that serves as one of the important tributaries feeding the São Francisco River system.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Rio Corrente
Target entity description: Rio Corrente is a significant river in Brazil that serves as one of the important tributaries feeding the São Francisco River system.
  • A. Rio Côa
    Rio Côa is a river in northeastern Portugal known for flowing through the Côa Valley, an area famous for its prehistoric open-air rock art sites.
  • B. Mundo River
    The Mundo River is a watercourse in southeastern Spain known for its scenic source at the Riópar waterfalls and for feeding into the Segura River.
  • C. Marta River
    The Marta River is a watercourse in central Italy that drains Lake Bolsena and flows southwest toward the Tyrrhenian Sea.
  • D. Rio Corgo
    Rio Corgo is a river in northern Portugal that flows through the Trás-os-Montes region before joining the Douro River.
  • E. Rio Soberbo
    Rio Soberbo is a river in the state of Rio de Janeiro, Brazil, known for flowing through the municipality of Guapimirim in the Serra dos Órgãos region.
  • 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_69d8839174188190909f190097207065 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3b0349bc88190938750f1e5af192a completed April 18, 2026, 4:24 p.m.
NED1 Entity disambiguation (via context triple) batch_6a071433204c819086b3c7263352dc1b completed May 15, 2026, 12:40 p.m.
NEDg Description generation batch_6a0714c3099c81909b009fe952d0de81 completed May 15, 2026, 12:42 p.m.
NED2 Entity disambiguation (via description) batch_6a07152aafb48190a767005628c6380a completed May 15, 2026, 12:44 p.m.
Created at: April 10, 2026, 5:21 a.m.