Triple
T13239335
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ter |
E315238
|
entity |
| Predicate | flowsThrough |
P225
|
FINISHED |
| Object |
Selva
Selva is a locality or region situated along the course of the Ter River, known for its riverine landscape.
|
E878040
|
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: Selva | Statement: [Ter, flowsThrough, Selva]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Selva Context triple: [Ter, flowsThrough, Selva]
-
A.
Selva
Selva is a coastal and inland comarca (county) in the province of Girona, Catalonia, known for its mix of Mediterranean beaches and forested interior landscapes.
-
B.
Selva Alta
Selva Alta is a high-elevation Amazonian rainforest zone in Peru characterized by steep terrain, dense cloud forests, and rich biodiversity.
-
C.
Ciluba
Ciluba is a Bantu language spoken primarily in the Democratic Republic of the Congo, especially in the Kasai region.
-
D.
Xingu Asuriní
Xingu Asuriní is an indigenous language of the Tupi–Guaraní family spoken by the Asuriní people living along Brazil’s Xingu River.
-
E.
Makushi
The Makushi are an Indigenous people of the Guiana Shield region, primarily living in southern Guyana and northern Brazil, known for their traditional subsistence farming, rich oral traditions, and close relationship with the rainforest environment.
- 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: Selva Triple: [Ter, flowsThrough, Selva]
Generated description
Selva is a locality or region situated along the course of the Ter River, known for its riverine landscape.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Selva Target entity description: Selva is a locality or region situated along the course of the Ter River, known for its riverine landscape.
-
A.
Selva
chosen
Selva is a coastal and inland comarca (county) in the province of Girona, Catalonia, known for its mix of Mediterranean beaches and forested interior landscapes.
-
B.
Selva Alta
Selva Alta is a high-elevation Amazonian rainforest zone in Peru characterized by steep terrain, dense cloud forests, and rich biodiversity.
-
C.
Ciluba
Ciluba is a Bantu language spoken primarily in the Democratic Republic of the Congo, especially in the Kasai region.
-
D.
Xingu Asuriní
Xingu Asuriní is an indigenous language of the Tupi–Guaraní family spoken by the Asuriní people living along Brazil’s Xingu River.
-
E.
Makushi
The Makushi are an Indigenous people of the Guiana Shield region, primarily living in southern Guyana and northern Brazil, known for their traditional subsistence farming, rich oral traditions, and close relationship with the rainforest environment.
- F. None of above.
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_69d806b1072881909e46bd212259c5f0 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98d5850ac8190849a51da39efe5be |
completed | April 10, 2026, 11:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6ff323a3c8190b46b24e69e653105 |
completed | May 3, 2026, 7:54 a.m. |
| NEDg | Description generation | batch_69f7013b3428819083c2bb6032aa08d4 |
completed | May 3, 2026, 8:03 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69f702b40f088190bc3c24321309dfb1 |
completed | May 3, 2026, 8:09 a.m. |
Created at: April 9, 2026, 9:23 p.m.