Triple
T23385797
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Western Area, Sierra Leone |
E593874
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object |
Tokeh
Tokeh is a coastal village in the Western Area of Sierra Leone known for its scenic beaches and growing tourism.
|
E1583196
|
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: Tokeh | Statement: [Western Area, Sierra Leone, contains, Tokeh]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tokeh Context triple: [Western Area, Sierra Leone, contains, Tokeh]
-
A.
Tajirika
Tajirika is a character in Ngũgĩ wa Thiong’o’s novel "Wizard of the Crow," depicted as an ambitious, corrupt businessman whose greed and opportunism satirize postcolonial African politics and capitalism.
-
B.
Takabisha
Takabisha is a record-breaking steel roller coaster in Japan renowned for its extremely steep drop and intense thrill elements.
-
C.
Toyapakeh
Toyapakeh is a renowned dive site off Nusa Penida in Bali, Indonesia, known for its rich coral reefs, clear waters, and diverse marine life including manta rays and mola mola.
-
D.
Tuktukan
Tuktukan is a barangay (village-level administrative division) in the city of Taguig in Metro Manila, Philippines.
-
E.
Bakoteh
Bakoteh is a residential neighborhood within the urban area of Serekunda in The Gambia.
- 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: Tokeh Triple: [Western Area, Sierra Leone, contains, Tokeh]
Generated description
Tokeh is a coastal village in the Western Area of Sierra Leone known for its scenic beaches and growing tourism.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Tokeh Target entity description: Tokeh is a coastal village in the Western Area of Sierra Leone known for its scenic beaches and growing tourism.
-
A.
Tajirika
Tajirika is a character in Ngũgĩ wa Thiong’o’s novel "Wizard of the Crow," depicted as an ambitious, corrupt businessman whose greed and opportunism satirize postcolonial African politics and capitalism.
-
B.
Takabisha
Takabisha is a record-breaking steel roller coaster in Japan renowned for its extremely steep drop and intense thrill elements.
-
C.
Toyapakeh
Toyapakeh is a renowned dive site off Nusa Penida in Bali, Indonesia, known for its rich coral reefs, clear waters, and diverse marine life including manta rays and mola mola.
-
D.
Tuktukan
Tuktukan is a barangay (village-level administrative division) in the city of Taguig in Metro Manila, Philippines.
-
E.
Bakoteh
Bakoteh is a residential neighborhood within the urban area of Serekunda in The Gambia.
- 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_69e25d2754fc819085deea939bde60ab |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1a498286c8190abfa381649812cf0 |
completed | April 29, 2026, 6:26 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0c5de7b5e081908f965d84cb11ed9d |
completed | May 19, 2026, 12:56 p.m. |
| NEDg | Description generation | batch_6a0c6086e718819093bbd0f3431739cf |
completed | May 19, 2026, 1:07 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0c60f685c881909ef5c259da2e661b |
completed | May 19, 2026, 1:09 p.m. |
Created at: April 17, 2026, 5:35 p.m.