Triple

T10486718
Position Surface form Disambiguated ID Type / Status
Subject Northern Niger E247318 entity
Predicate containsTown P847 FINISHED
Object Dirkou
Dirkou is a remote oasis town in northeastern Niger that serves as a key stopover on trans-Saharan migration and trade routes across the Sahara Desert.
E866923 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: Dirkou | Statement: [Northern Niger, containsTown, Dirkou]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dirkou
Context triple: [Northern Niger, containsTown, Dirkou]
  • A. Doncieux
    Doncieux is a French surname most notably associated with Camille Doncieux, the first wife and frequent model of painter Claude Monet.
  • B. Kouneli
    Kouneli is a small Greek island in the Echinades group in the Ionian Sea.
  • C. Ozinga
    Ozinga is a Dutch surname most notably associated with individuals such as Sjoukje Ozinga.
  • D. Bittou
    Bittou is a town in Burkina Faso known for its role as a regional trading center and its international town-twinning links with European municipalities.
  • E. Makokou
    Makokou is a small town in northeastern Gabon that serves as a key access point to the surrounding rainforest and protected areas.
  • 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: Dirkou
Triple: [Northern Niger, containsTown, Dirkou]
Generated description
Dirkou is a remote oasis town in northeastern Niger that serves as a key stopover on trans-Saharan migration and trade routes across the Sahara Desert.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Dirkou
Target entity description: Dirkou is a remote oasis town in northeastern Niger that serves as a key stopover on trans-Saharan migration and trade routes across the Sahara Desert.
  • A. Doncieux
    Doncieux is a French surname most notably associated with Camille Doncieux, the first wife and frequent model of painter Claude Monet.
  • B. Kouneli
    Kouneli is a small Greek island in the Echinades group in the Ionian Sea.
  • C. Ozinga
    Ozinga is a Dutch surname most notably associated with individuals such as Sjoukje Ozinga.
  • D. Bittou
    Bittou is a town in Burkina Faso known for its role as a regional trading center and its international town-twinning links with European municipalities.
  • E. Makokou
    Makokou is a small town in northeastern Gabon that serves as a key access point to the surrounding rainforest and protected areas.
  • 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_69d381c309b88190af78aa681cf6a4c2 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d5096a4d3481908e9c319f6cdce4f1 completed April 7, 2026, 1:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69d8dc8c73748190b97c78af6cf142d9 completed April 10, 2026, 11:18 a.m.
NEDg Description generation batch_69d8e8c81bdc8190b6b6dfe00025b514 completed April 10, 2026, 12:10 p.m.
NED2 Entity disambiguation (via description) batch_69d901e1ecf88190acd24a0e20462cb9 completed April 10, 2026, 1:57 p.m.
Created at: April 6, 2026, 12:23 p.m.