Triple

T10172605
Position Surface form Disambiguated ID Type / Status
Subject Serekunda E235366 entity
Predicate hasRoadConnectionTo P11435 FINISHED
Object Bakau
Bakau is a coastal town in The Gambia known for its beaches, botanical gardens, and the popular Kachikally Crocodile Pool.
 E846680 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: Bakau | Statement: [Serekunda, hasRoadConnectionTo, Bakau]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Bakau
Context triple: [Serekunda, hasRoadConnectionTo, Bakau]
  • A. Kabaena
    Kabaena is an island in Indonesia known for its location off the coast of Sulawesi and its mix of coastal and hilly landscapes.
  • B. Baaka
    Baaka is the traditional Aboriginal name for the Darling River, one of the major inland rivers of southeastern Australia.
  • C. Kalabahi
    Kalabahi is the main town and administrative center on Alor Island in Indonesia’s East Nusa Tenggara province.
  • D. Bako
    Bako is the given name of Bako Sahakyan, a politician known for serving as the president of the self-proclaimed Republic of Artsakh (Nagorno-Karabakh).
  • E. Bakari
    Bakari is the middle name of American actor and filmmaker Michael B. Jordan, known for roles in films like "Creed" and "Black Panther."
  • 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: Bakau
Triple: [Serekunda, hasRoadConnectionTo, Bakau]
Generated description
Bakau is a coastal town in The Gambia known for its beaches, botanical gardens, and the popular Kachikally Crocodile Pool.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Bakau
Target entity description: Bakau is a coastal town in The Gambia known for its beaches, botanical gardens, and the popular Kachikally Crocodile Pool.
  • A. Kabaena
    Kabaena is an island in Indonesia known for its location off the coast of Sulawesi and its mix of coastal and hilly landscapes.
  • B. Baaka
    Baaka is the traditional Aboriginal name for the Darling River, one of the major inland rivers of southeastern Australia.
  • C. Kalabahi
    Kalabahi is the main town and administrative center on Alor Island in Indonesia’s East Nusa Tenggara province.
  • D. Bako
    Bako is the given name of Bako Sahakyan, a politician known for serving as the president of the self-proclaimed Republic of Artsakh (Nagorno-Karabakh).
  • E. Bakari
    Bakari is the middle name of American actor and filmmaker Michael B. Jordan, known for roles in films like "Creed" and "Black Panther."
  • 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_69ca84ceafd0819085828600e11bed6b completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cdec9f6dd8819081588600499165ee completed April 2, 2026, 4:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69d3178844c48190af952ac30a4d6d97 completed April 6, 2026, 2:16 a.m.
NEDg Description generation batch_69d318fbb3048190acdb28f18c5a215a completed April 6, 2026, 2:22 a.m.
NED2 Entity disambiguation (via description) batch_69d319687fac81909f8174ebfc84e737 completed April 6, 2026, 2:24 a.m.
Created at: March 30, 2026, 9:10 p.m.