Triple

T2353822
Position Surface form Disambiguated ID Type / Status
Subject Achuar-Shiwiar language E47507 entity
Predicate isSpokenAlong P38694 FINISHED
Object Pastaza River region
The Pastaza River region is an area of the upper Amazon Basin spanning parts of Ecuador and Peru, known for its Indigenous communities, rich rainforest biodiversity, and complex riverine ecosystems.
E257661 NE FINISHED

How this triple was built (5 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: Pastaza River region | Statement: [Achuar-Shiwiar language, isSpokenAlong, Pastaza River region]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pastaza River region
Context triple: [Achuar-Shiwiar language, isSpokenAlong, Pastaza River region]
  • A. Sumapaz region
    The Sumapaz region is a rural area of central Colombia known for its high Andean landscapes, agricultural production, and proximity to the vast Sumapaz páramo, one of the world’s largest high-mountain wetlands.
  • B. Cordillera del Cóndor region
    The Cordillera del Cóndor region is a biodiverse and mineral-rich mountain range along the Ecuador–Peru border, known for its unique sandstone plateaus and long-standing territorial and conservation significance.
  • C. Atrato River basin
    The Atrato River basin is a biodiverse and rainforest-rich watershed in northwestern Colombia, known for its dense river network, Afro-Colombian and Indigenous communities, and significant ecological and cultural importance.
  • D. Magdalena River valley
    The Magdalena River valley is a major geographic region in Colombia characterized by its long, fertile river basin that has historically served as a crucial corridor for exploration, settlement, and trade.
  • E. Central Valley of Tarija
    The Central Valley of Tarija is a fertile wine-producing region in southern Bolivia known for its mild climate, vineyards, and scenic Andean landscapes.
  • 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: Pastaza River region
Triple: [Achuar-Shiwiar language, isSpokenAlong, Pastaza River region]
Generated description
The Pastaza River region is an area of the upper Amazon Basin spanning parts of Ecuador and Peru, known for its Indigenous communities, rich rainforest biodiversity, and complex riverine ecosystems.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Pastaza River region
Target entity description: The Pastaza River region is an area of the upper Amazon Basin spanning parts of Ecuador and Peru, known for its Indigenous communities, rich rainforest biodiversity, and complex riverine ecosystems.
  • A. Sumapaz region
    The Sumapaz region is a rural area of central Colombia known for its high Andean landscapes, agricultural production, and proximity to the vast Sumapaz páramo, one of the world’s largest high-mountain wetlands.
  • B. Cordillera del Cóndor region
    The Cordillera del Cóndor region is a biodiverse and mineral-rich mountain range along the Ecuador–Peru border, known for its unique sandstone plateaus and long-standing territorial and conservation significance.
  • C. Atrato River basin
    The Atrato River basin is a biodiverse and rainforest-rich watershed in northwestern Colombia, known for its dense river network, Afro-Colombian and Indigenous communities, and significant ecological and cultural importance.
  • D. Magdalena River valley
    The Magdalena River valley is a major geographic region in Colombia characterized by its long, fertile river basin that has historically served as a crucial corridor for exploration, settlement, and trade.
  • E. Central Valley of Tarija
    The Central Valley of Tarija is a fertile wine-producing region in southern Bolivia known for its mild climate, vineyards, and scenic Andean landscapes.
  • F. None of above. chosen
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: isSpokenAlong
Context triple: [Achuar-Shiwiar language, isSpokenAlong, Pastaza River region]
  • A. spokenAlong
    Indicates that two or more languages are used concurrently or within the same context in a particular place, time, or situation.
  • B. isSpokenAs
    Indicates that one entity is used as the spoken or verbal form of another entity (e.g., a word, name, or phrase).
  • C. includesSpokenWordAppearanceBy
    Indicates that something (such as a work, recording, or event) contains an instance where a person or entity appears through spoken words.
  • D. usedInSpokenForm
    Indicates that something (such as a word, name, or expression) is employed in spoken language or oral communication.
  • E. spokenOn
    Indicates that an utterance or speech act occurred at or during a specific time or date.
  • F. None of above. chosen

Provenance (7 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_69a88a1b678c8190bce986922ba60ce0 completed March 4, 2026, 7:38 p.m.
NER Named-entity recognition batch_69abcb802da08190980100444010f91e completed March 7, 2026, 6:53 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae9633ce3c81908581e7e0f8211ac1 completed March 9, 2026, 9:43 a.m.
NEDg Description generation batch_69ae971aa3bc8190b0b8b216106dca90 completed March 9, 2026, 9:47 a.m.
NED2 Entity disambiguation (via description) batch_69ae9795cf048190bc7a01ef86c12138 completed March 9, 2026, 9:49 a.m.
PD Predicate disambiguation batch_69abc5981ce48190a3f7852d28276e11 completed March 7, 2026, 6:28 a.m.
PDg Predicate description generation batch_69abcb7ebb708190ba7edffee3c45d8b completed March 7, 2026, 6:53 a.m.
Created at: March 4, 2026, 7:54 p.m.