Triple
T20357002
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Munduruku people |
E496675
|
entity |
| Predicate | traditionalTerritory |
P1103
|
FINISHED |
| Object | Tapajós River basin |
—
|
NE NERFINISHED |
How this triple was built (3 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: Tapajós River basin | Statement: [Munduruku people, traditionalTerritory, Tapajós River basin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tapajós River basin Context triple: [Munduruku people, traditionalTerritory, Tapajós River basin]
-
A.
Balsas River basin
The Balsas River basin is a major drainage basin in south-central Mexico centered on the Balsas River, encompassing diverse climates and landscapes and supporting extensive agriculture and human settlements.
-
B.
Rio Pardo basin
The Rio Pardo basin is a river drainage system in the state of Rio Grande do Sul, Brazil, encompassing municipalities such as Santa Cruz do Sul and supporting regional agriculture and settlements.
-
C.
Sucio River basin
The Sucio River basin is a drainage area in western El Salvador that collects the waters of the Sucio River within La Libertad Department, supporting local ecosystems and nearby communities.
-
D.
Vaupés River basin
The Vaupés River basin is a remote, forested region of the northwest Amazon, spanning parts of Colombia and Brazil and known for its rich biodiversity and dense concentration of Indigenous communities.
-
E.
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.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Tapajós River basin Target entity description: The Tapajós River basin is a vast Amazonian watershed in Brazil known for its rich biodiversity and as the ancestral homeland of Indigenous groups such as the Munduruku people.
-
A.
Balsas River basin
The Balsas River basin is a major drainage basin in south-central Mexico centered on the Balsas River, encompassing diverse climates and landscapes and supporting extensive agriculture and human settlements.
-
B.
Rio Pardo basin
The Rio Pardo basin is a river drainage system in the state of Rio Grande do Sul, Brazil, encompassing municipalities such as Santa Cruz do Sul and supporting regional agriculture and settlements.
-
C.
Sucio River basin
The Sucio River basin is a drainage area in western El Salvador that collects the waters of the Sucio River within La Libertad Department, supporting local ecosystems and nearby communities.
-
D.
Vaupés River basin
The Vaupés River basin is a remote, forested region of the northwest Amazon, spanning parts of Colombia and Brazil and known for its rich biodiversity and dense concentration of Indigenous communities.
-
E.
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.
- F. None of above. chosen
Provenance (2 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_69e0b4a3f7f48190b37f354574028ca6 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e67854c0448190ab10363f8a218afb |
completed | April 20, 2026, 7:02 p.m. |
Created at: April 16, 2026, 11:25 a.m.