Triple
T14583542
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yankari National Park |
E342255
|
entity |
| Predicate | traversedBy |
P225
|
FINISHED |
| Object |
Gaji River
Gaji River is a river in northeastern Nigeria that flows through Yankari National Park, supporting its wildlife and ecosystems.
|
E1591110
|
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: Gaji River | Statement: [Yankari National Park, traversedBy, Gaji River]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gaji River Context triple: [Yankari National Park, traversedBy, Gaji River]
-
A.
Korang River
Korang River is a stream in Pakistan that serves as a primary inflow to Rawal Lake near Islamabad.
-
B.
Coongan River
The Coongan River is a watercourse in the Pilbara region of Western Australia that flows through arid landscapes before joining the De Grey River.
-
C.
Warta River
The Warta River is a major river in western and central Poland, flowing through cities such as Poznań before joining the Oder River.
-
D.
Leie River
The Leie River is a scenic waterway in Belgium that flows through the historic city of Ghent, where it is lined by the famous medieval quays of Graslei and Korenlei.
-
E.
Strickland River
Strickland River is a major river in Papua New Guinea that flows through remote rainforest regions before joining the Fly River system.
- 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: Gaji River Triple: [Yankari National Park, traversedBy, Gaji River]
Generated description
Gaji River is a river in northeastern Nigeria that flows through Yankari National Park, supporting its wildlife and ecosystems.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Gaji River Target entity description: Gaji River is a river in northeastern Nigeria that flows through Yankari National Park, supporting its wildlife and ecosystems.
-
A.
Korang River
Korang River is a stream in Pakistan that serves as a primary inflow to Rawal Lake near Islamabad.
-
B.
Coongan River
The Coongan River is a watercourse in the Pilbara region of Western Australia that flows through arid landscapes before joining the De Grey River.
-
C.
Warta River
The Warta River is a major river in western and central Poland, flowing through cities such as Poznań before joining the Oder River.
-
D.
Leie River
The Leie River is a scenic waterway in Belgium that flows through the historic city of Ghent, where it is lined by the famous medieval quays of Graslei and Korenlei.
-
E.
Strickland River
Strickland River is a major river in Papua New Guinea that flows through remote rainforest regions before joining the Fly River system.
- 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_69d822ddc0f081909cd8163c7de298cd |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb4209b988190ad2a7b2dead8ffed |
completed | April 14, 2026, 9:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0cdf1fb1208190ab1f9a616d4134a2 |
completed | May 19, 2026, 10:07 p.m. |
| NEDg | Description generation | batch_6a0ce13763b4819085da4b36ae659afb |
completed | May 19, 2026, 10:16 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0ce1bcd440819087344b83bb0ac0e8 |
completed | May 19, 2026, 10:18 p.m. |
Created at: April 10, 2026, 1:24 a.m.