Triple
T17836068
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mahi River |
E445386
|
entity |
| Predicate | hasDam |
P8736
|
FINISHED |
| Object |
Kadana Dam
Kadana Dam is a major multi-purpose dam in Gujarat, India, built on the Mahi River for irrigation, hydroelectric power generation, and flood control.
|
E1291372
|
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: Kadana Dam | Statement: [Mahi River, hasDam, Kadana Dam]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kadana Dam Context triple: [Mahi River, hasDam, Kadana Dam]
-
A.
Koka Dam
Koka Dam is a major hydroelectric and irrigation dam in Ethiopia that creates the Koka Reservoir on the Awash River.
-
B.
Kindaruma Dam
Kindaruma Dam is one of Kenya’s major hydroelectric power stations on the Tana River, contributing significantly to the country’s electricity generation.
-
C.
Ukai Dam
Ukai Dam is a major multi-purpose reservoir and hydroelectric dam in Gujarat, India, built on the Tapi River for irrigation, power generation, and flood control.
-
D.
Bokaa Dam
Bokaa Dam is a major water reservoir in Botswana that supplies drinking water and supports irrigation for communities in and around the Kgatleng District.
-
E.
Ikeda Dam
Ikeda Dam is a major hydroelectric dam in Japan known for generating power and regulating water flow on the Yoshino River.
- 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: Kadana Dam Triple: [Mahi River, hasDam, Kadana Dam]
Generated description
Kadana Dam is a major multi-purpose dam in Gujarat, India, built on the Mahi River for irrigation, hydroelectric power generation, and flood control.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Kadana Dam Target entity description: Kadana Dam is a major multi-purpose dam in Gujarat, India, built on the Mahi River for irrigation, hydroelectric power generation, and flood control.
-
A.
Koka Dam
Koka Dam is a major hydroelectric and irrigation dam in Ethiopia that creates the Koka Reservoir on the Awash River.
-
B.
Kindaruma Dam
Kindaruma Dam is one of Kenya’s major hydroelectric power stations on the Tana River, contributing significantly to the country’s electricity generation.
-
C.
Ukai Dam
Ukai Dam is a major multi-purpose reservoir and hydroelectric dam in Gujarat, India, built on the Tapi River for irrigation, power generation, and flood control.
-
D.
Bokaa Dam
Bokaa Dam is a major water reservoir in Botswana that supplies drinking water and supports irrigation for communities in and around the Kgatleng District.
-
E.
Ikeda Dam
Ikeda Dam is a major hydroelectric dam in Japan known for generating power and regulating water flow on the Yoshino River.
- 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_69d8b9f1a6d881909f024bc603111cdb |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e48d27f8908190bf48a8153756effa |
completed | April 19, 2026, 8:07 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0306fa32e481908ef71c18b6f37d59 |
completed | May 12, 2026, 10:54 a.m. |
| NEDg | Description generation | batch_6a030804acf081908b4f00aa4e45e842 |
completed | May 12, 2026, 10:59 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0308a29f1081909a44c221aefb723c |
completed | May 12, 2026, 11:01 a.m. |
Created at: April 10, 2026, 10:16 a.m.