Triple

T11578447
Position Surface form Disambiguated ID Type / Status
Subject Dogon languages E274563 entity
Predicate hasSubgroup P747 FINISHED
Object Nanga
Nanga is a subgroup of the Dogon languages spoken by the Dogon people of Mali in West Africa.
E939904 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: Nanga | Statement: [Dogon languages, hasSubgroup, Nanga]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nanga
Context triple: [Dogon languages, hasSubgroup, Nanga]
  • A. Mount Ntringui
    Mount Ntringui is a volcanic peak on the island of Anjouan in the Comoros, known for its lush forests and prominence in the island’s rugged landscape.
  • B. Mount Wilis
    Mount Wilis is a solitary, inactive stratovolcano in East Java, Indonesia, known for its forested slopes and surrounding rural highland communities.
  • C. Mount Adatara
    Mount Adatara is an active stratovolcano in Japan’s Tohoku region, known for its scenic alpine landscapes and popular hiking trails.
  • D. Mount Muna
    Mount Muna is the highest peak on Alor Island in Indonesia, known as a prominent landmark in the island’s rugged volcanic landscape.
  • E. Anai Mudi
    Anai Mudi is the highest peak in South India, located in the Western Ghats of Kerala and known for its rich biodiversity and scenic trekking routes.
  • 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: Nanga
Triple: [Dogon languages, hasSubgroup, Nanga]
Generated description
Nanga is a subgroup of the Dogon languages spoken by the Dogon people of Mali in West Africa.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Nanga
Target entity description: Nanga is a subgroup of the Dogon languages spoken by the Dogon people of Mali in West Africa.
  • A. Mount Ntringui
    Mount Ntringui is a volcanic peak on the island of Anjouan in the Comoros, known for its lush forests and prominence in the island’s rugged landscape.
  • B. Mount Wilis
    Mount Wilis is a solitary, inactive stratovolcano in East Java, Indonesia, known for its forested slopes and surrounding rural highland communities.
  • C. Mount Adatara
    Mount Adatara is an active stratovolcano in Japan’s Tohoku region, known for its scenic alpine landscapes and popular hiking trails.
  • D. Mount Muna
    Mount Muna is the highest peak on Alor Island in Indonesia, known as a prominent landmark in the island’s rugged volcanic landscape.
  • E. Anai Mudi
    Anai Mudi is the highest peak in South India, located in the Western Ghats of Kerala and known for its rich biodiversity and scenic trekking routes.
  • 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_69d6aae5ac3c81908d2b0a3a665665b2 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8904b46288190890ecafd6ceb0c3d completed April 10, 2026, 5:53 a.m.
NED1 Entity disambiguation (via context triple) batch_69ef12f0661081909c31de2c2cd304e3 completed April 27, 2026, 7:40 a.m.
NEDg Description generation batch_69ef354b3b3c8190b1c91dbf9c705a7d completed April 27, 2026, 10:07 a.m.
NED2 Entity disambiguation (via description) batch_69ef5170ce9881908f2ecf3d5ada809a completed April 27, 2026, 12:07 p.m.
Created at: April 8, 2026, 9:38 p.m.