Triple

T1340491
Position Surface form Disambiguated ID Type / Status
Subject Kwa languages E28451 entity
Predicate hasSubgroup P747 FINISHED
Object Sehwi language
The Sehwi language is a Niger-Congo language spoken primarily by the Sehwi people of western Ghana.
E155050 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: Sehwi language | Statement: [Kwa languages, hasSubgroup, Sehwi language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sehwi language
Context triple: [Kwa languages, hasSubgroup, Sehwi language]
  • A. Kavalan language
    The Kavalan language is an endangered Austronesian language of the indigenous Kavalan people of northeastern Taiwan.
  • B. Chimariko language
    The Chimariko language is an extinct Native American language once spoken in northwestern California, often classified within the proposed Hokan language family.
  • C. Seediq language
    The Seediq language is an Austronesian language spoken by the Seediq indigenous people of central Taiwan, known for its complex verb morphology and rich system of focus and voice.
  • D. Kawaiisu language
    Kawaiisu language is an endangered Uto-Aztecan language traditionally spoken by the Kawaiisu people of southern California.
  • E. Sakizaya language
    The Sakizaya language is an indigenous Austronesian language spoken by the Sakizaya people of eastern Taiwan.
  • 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: Sehwi language
Triple: [Kwa languages, hasSubgroup, Sehwi language]
Generated description
The Sehwi language is a Niger-Congo language spoken primarily by the Sehwi people of western Ghana.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sehwi language
Target entity description: The Sehwi language is a Niger-Congo language spoken primarily by the Sehwi people of western Ghana.
  • A. Kavalan language
    The Kavalan language is an endangered Austronesian language of the indigenous Kavalan people of northeastern Taiwan.
  • B. Chimariko language
    The Chimariko language is an extinct Native American language once spoken in northwestern California, often classified within the proposed Hokan language family.
  • C. Seediq language
    The Seediq language is an Austronesian language spoken by the Seediq indigenous people of central Taiwan, known for its complex verb morphology and rich system of focus and voice.
  • D. Hoanya language
    The Hoanya language is an extinct Austronesian language once spoken by the Hoanya people of western Taiwan and classified among the indigenous Formosan languages.
  • E. Kawaiisu language
    Kawaiisu language is an endangered Uto-Aztecan language traditionally spoken by the Kawaiisu people of southern California.
  • 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_69a49854eb3481908c7d56b2e449a290 completed March 1, 2026, 7:49 p.m.
NER Named-entity recognition batch_69a4c21490488190b4281a16c87677d1 completed March 1, 2026, 10:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69acc6305c988190830dd535726c6338 completed March 8, 2026, 12:43 a.m.
NEDg Description generation batch_69acc91793688190a223365d50498cc7 completed March 8, 2026, 12:55 a.m.
NED2 Entity disambiguation (via description) batch_69acc9b8c86c8190bc3526b85604884d completed March 8, 2026, 12:58 a.m.
Created at: March 1, 2026, 7:56 p.m.