Triple

T10071590
Position Surface form Disambiguated ID Type / Status
Subject São Francisco River E213640 entity
Predicate hasCityOnBank P7935 FINISHED
Object Propriá
Propriá is a municipality in the Brazilian state of Sergipe, known for its riverside location and economic activities linked to the São Francisco River.
E839361 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: Propriá | Statement: [São Francisco River, hasCityOnBank, Propriá]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Propriá
Context triple: [São Francisco River, hasCityOnBank, Propriá]
  • A. Parea
    Parea is a small coastal village on the island of Huahine in French Polynesia, known for its tranquil beaches and traditional Polynesian atmosphere.
  • B. Nisaea
    Nisaea was the port town and harbor of ancient Megara in Greece, serving as its main maritime outlet on the Saronic Gulf.
  • C. Parecís
    Parecís is an Arawakan language spoken by the Paresí (Haliti) Indigenous people of Brazil, primarily in the state of Mato Grosso.
  • D. Soroa
    Soroa is a small Cuban village and popular ecotourism destination known for its lush mountain scenery, waterfalls, and orchid garden.
  • E. Pamiris
    Pamiris are an Iranian ethnic group native to the mountainous Pamir region of Central Asia, known for their distinct Eastern Iranian languages and cultural traditions.
  • 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: Propriá
Triple: [São Francisco River, hasCityOnBank, Propriá]
Generated description
Propriá is a municipality in the Brazilian state of Sergipe, known for its riverside location and economic activities linked to the São Francisco River.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Propriá
Target entity description: Propriá is a municipality in the Brazilian state of Sergipe, known for its riverside location and economic activities linked to the São Francisco River.
  • A. Parea
    Parea is a small coastal village on the island of Huahine in French Polynesia, known for its tranquil beaches and traditional Polynesian atmosphere.
  • B. Nisaea
    Nisaea was the port town and harbor of ancient Megara in Greece, serving as its main maritime outlet on the Saronic Gulf.
  • C. Parecís
    Parecís is an Arawakan language spoken by the Paresí (Haliti) Indigenous people of Brazil, primarily in the state of Mato Grosso.
  • D. Soroa
    Soroa is a small Cuban village and popular ecotourism destination known for its lush mountain scenery, waterfalls, and orchid garden.
  • E. Pamiris
    Pamiris are an Iranian ethnic group native to the mountainous Pamir region of Central Asia, known for their distinct Eastern Iranian languages and cultural traditions.
  • 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_69ca839add308190b57d53b4ec21f2d0 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cdd01279388190b94c8def00425c78 completed April 2, 2026, 2:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69d29aaa61308190b134b49a6c1c1131 completed April 5, 2026, 5:23 p.m.
NEDg Description generation batch_69d29e8617c08190bf4fb02ac40caba3 completed April 5, 2026, 5:40 p.m.
NED2 Entity disambiguation (via description) batch_69d29f20b2f48190906d7e53fb1e5544 completed April 5, 2026, 5:42 p.m.
Created at: March 30, 2026, 8:59 p.m.