Triple
T22994304
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Butare |
E572140
|
entity |
| Predicate | hasAlternativeName |
P39
|
FINISHED |
| Object |
Huye
Huye is a city in southern Rwanda known as an important academic and cultural center, home to the University of Rwanda’s main campus and several historical and religious sites.
|
E1565211
|
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: Huye | Statement: [Butare, hasAlternativeName, Huye]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Huye Context triple: [Butare, hasAlternativeName, Huye]
-
A.
Ruhengeri
Ruhengeri is the former name of Musanze, a city in northern Rwanda known as a gateway to Volcanoes National Park and its mountain gorillas.
-
B.
Kinshaldy
Kinshaldy is a coastal area in Fife, Scotland, known for its expansive sandy beach, dunes, and proximity to Tentsmuir Forest.
-
C.
Buduburam
Buduburam is a town in Ghana best known for hosting a large refugee settlement, particularly for Liberian refugees, and has grown into a diverse suburban community.
-
D.
Balaka
Balaka is a town in southern Malawi that serves as an important local commercial and transportation hub.
-
E.
Karume
Karume is a Swahili surname most prominently associated with Abeid Karume, the first president of Zanzibar and a key figure in Tanzanian political history.
- 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: Huye Triple: [Butare, hasAlternativeName, Huye]
Generated description
Huye is a city in southern Rwanda known as an important academic and cultural center, home to the University of Rwanda’s main campus and several historical and religious sites.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Huye Target entity description: Huye is a city in southern Rwanda known as an important academic and cultural center, home to the University of Rwanda’s main campus and several historical and religious sites.
-
A.
Ruhengeri
Ruhengeri is the former name of Musanze, a city in northern Rwanda known as a gateway to Volcanoes National Park and its mountain gorillas.
-
B.
Kinshaldy
Kinshaldy is a coastal area in Fife, Scotland, known for its expansive sandy beach, dunes, and proximity to Tentsmuir Forest.
-
C.
Buduburam
Buduburam is a town in Ghana best known for hosting a large refugee settlement, particularly for Liberian refugees, and has grown into a diverse suburban community.
-
D.
Balaka
Balaka is a town in southern Malawi that serves as an important local commercial and transportation hub.
-
E.
Karume
Karume is a Swahili surname most prominently associated with Abeid Karume, the first president of Zanzibar and a key figure in Tanzanian political history.
- 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_69e245b535808190adef8a9df3c584db |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f182f1940c8190a5645ee8d8e5e063 |
completed | April 29, 2026, 4:02 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0bd37cd30c8190ae2fa99f18b59b94 |
completed | May 19, 2026, 3:05 a.m. |
| NEDg | Description generation | batch_6a0bd43af7948190886a30522f3b6c8a |
completed | May 19, 2026, 3:08 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0bd503b1588190979b9895327a3475 |
completed | May 19, 2026, 3:12 a.m. |
Created at: April 17, 2026, 3:50 p.m.