Triple

T22618025
Position Surface form Disambiguated ID Type / Status
Subject Savannah Region E558198 entity
Predicate hasSettlement P1068 FINISHED
Object Larabanga
Larabanga is a historic village in northern Ghana best known for its ancient mud-and-stick mosque, one of the oldest Islamic structures in West Africa.
E1546734 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: Larabanga | Statement: [Savannah Region, hasSettlement, Larabanga]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Larabanga
Context triple: [Savannah Region, hasSettlement, Larabanga]
  • A. Kaolack
    Kaolack is a major city in western Senegal known as a regional commercial hub and center of peanut trade.
  • B. Bignona
    Bignona is a town in southern Senegal’s Casamance region, known as a local center of trade and cultural diversity.
  • C. Djenné Songhay
    Djenné Songhay is a regional variety of the Songhay language spoken around the town of Djenné in Mali.
  • D. Djenné
    Djenné is an ancient Malian town renowned for its mud-brick architecture and historic Great Mosque, a UNESCO World Heritage site and one of the most famous examples of Sudano-Sahelian architecture.
  • E. Ambouli
    Ambouli is a district of Djibouti City that hosts the country’s main international airport and related urban infrastructure.
  • 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: Larabanga
Triple: [Savannah Region, hasSettlement, Larabanga]
Generated description
Larabanga is a historic village in northern Ghana best known for its ancient mud-and-stick mosque, one of the oldest Islamic structures in West Africa.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Larabanga
Target entity description: Larabanga is a historic village in northern Ghana best known for its ancient mud-and-stick mosque, one of the oldest Islamic structures in West Africa.
  • A. Kaolack
    Kaolack is a major city in western Senegal known as a regional commercial hub and center of peanut trade.
  • B. Bignona
    Bignona is a town in southern Senegal’s Casamance region, known as a local center of trade and cultural diversity.
  • C. Djenné Songhay
    Djenné Songhay is a regional variety of the Songhay language spoken around the town of Djenné in Mali.
  • D. Djenné
    Djenné is an ancient Malian town renowned for its mud-brick architecture and historic Great Mosque, a UNESCO World Heritage site and one of the most famous examples of Sudano-Sahelian architecture.
  • E. Ambouli
    Ambouli is a district of Djibouti City that hosts the country’s main international airport and related urban infrastructure.
  • 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_69e24545a8e08190bfa7482a2c725ff1 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f167ef7a148190870334af9c8b79a4 completed April 29, 2026, 2:07 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b4e018e04819086ec5d885fb76f67 completed May 18, 2026, 5:36 p.m.
NEDg Description generation batch_6a0b513c2908819087b05efdbf8688aa completed May 18, 2026, 5:49 p.m.
NED2 Entity disambiguation (via description) batch_6a0b51db01948190b968a3f289419776 completed May 18, 2026, 5:52 p.m.
Created at: April 17, 2026, 2:59 p.m.