Triple

T17193485
Position Surface form Disambiguated ID Type / Status
Subject Mende language E417285 entity
Predicate hasDialects P4251 FINISHED
Object Sewa-Mende
Sewa-Mende is a regional dialect of the Mende language spoken primarily in parts of Sierra Leone.
E1255494 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: Sewa-Mende | Statement: [Mende language, hasDialects, Sewa-Mende]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sewa-Mende
Context triple: [Mende language, hasDialects, Sewa-Mende]
  • A. Gōṇḍī
    Gōṇḍī is a South-Central Dravidian language spoken primarily by the Gondi people in central India.
  • B. Moirang
    Moirang is a historic town in Manipur, India, known for its cultural heritage and proximity to the famous Loktak Lake.
  • C. Ga-Dangme
    Ga-Dangme are an ethnic group of southeastern Ghana, historically known as coastal traders and fishermen with a rich cultural heritage and distinct Ga and Dangme language varieties.
  • D. Bikhauti
    Bikhauti is a traditional regional festival celebrated in the Garhwal area of Uttarakhand, India, marked by local religious rituals and community gatherings.
  • E. Sonowal Kachari
    The Sonowal Kachari are an indigenous ethnic community of Assam in Northeast India, historically associated with gold-washing and rich agrarian and cultural traditions.
  • 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: Sewa-Mende
Triple: [Mende language, hasDialects, Sewa-Mende]
Generated description
Sewa-Mende is a regional dialect of the Mende language spoken primarily in parts of Sierra Leone.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sewa-Mende
Target entity description: Sewa-Mende is a regional dialect of the Mende language spoken primarily in parts of Sierra Leone.
  • A. Gōṇḍī
    Gōṇḍī is a South-Central Dravidian language spoken primarily by the Gondi people in central India.
  • B. Moirang
    Moirang is a historic town in Manipur, India, known for its cultural heritage and proximity to the famous Loktak Lake.
  • C. Ga-Dangme
    Ga-Dangme are an ethnic group of southeastern Ghana, historically known as coastal traders and fishermen with a rich cultural heritage and distinct Ga and Dangme language varieties.
  • D. Bikhauti
    Bikhauti is a traditional regional festival celebrated in the Garhwal area of Uttarakhand, India, marked by local religious rituals and community gatherings.
  • E. Sonowal Kachari
    The Sonowal Kachari are an indigenous ethnic community of Assam in Northeast India, historically associated with gold-washing and rich agrarian and cultural traditions.
  • 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_69d886d6ba8c819093215917b3d01689 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e42da93bf88190b60b658087779d36 completed April 19, 2026, 1:19 a.m.
NED1 Entity disambiguation (via context triple) batch_6a015fd393ac8190afc4c076b6cf60ba completed May 11, 2026, 4:49 a.m.
NEDg Description generation batch_6a016173b06081908fa80d2e530d6c2c completed May 11, 2026, 4:56 a.m.
NED2 Entity disambiguation (via description) batch_6a0161d384f481909db41bc8c1d263a7 completed May 11, 2026, 4:57 a.m.
Created at: April 10, 2026, 5:38 a.m.