Triple

T1871183
Position Surface form Disambiguated ID Type / Status
Subject Toubou E39037 entity
Predicate primaryLanguage P238 FINISHED
Object Teda language
The Teda language is a Saharan language spoken primarily by the Teda (northern Toubou) people of the Tibesti region in Chad and southern Libya.
 E208969 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: Teda language | Statement: [Toubou, primaryLanguage, Teda language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Teda language
Context triple: [Toubou, primaryLanguage, Teda language]
  • A. Logba language
    The Logba language is a Niger-Congo language spoken by the Logba people of southeastern Ghana.
  • B. Teso language
    Teso language is an Eastern Nilotic language spoken primarily by the Iteso people in eastern Uganda and western Kenya.
  • C. Kaado language
    The Kaado language is a regional variety within the Songhay language family spoken by communities in parts of West Africa.
  • D. Yola language
    The Yola language was an extinct West Germanic language once spoken in County Wexford, Ireland, that preserved many archaic features derived from early English settlers.
  • E. Baliledu language
    The Baliledu language is an Austronesian language of the Bima–Sumba subgroup spoken by a local community in eastern Indonesia.
  • 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: Teda language
Triple: [Toubou, primaryLanguage, Teda language]
Generated description
The Teda language is a Saharan language spoken primarily by the Teda (northern Toubou) people of the Tibesti region in Chad and southern Libya.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Teda language
Target entity description: The Teda language is a Saharan language spoken primarily by the Teda (northern Toubou) people of the Tibesti region in Chad and southern Libya.
  • A. Logba language
    The Logba language is a Niger-Congo language spoken by the Logba people of southeastern Ghana.
  • B. Teso language
    Teso language is an Eastern Nilotic language spoken primarily by the Iteso people in eastern Uganda and western Kenya.
  • C. Kaado language
    The Kaado language is a regional variety within the Songhay language family spoken by communities in parts of West Africa.
  • D. Yola language
    The Yola language was an extinct West Germanic language once spoken in County Wexford, Ireland, that preserved many archaic features derived from early English settlers.
  • E. Baliledu language
    The Baliledu language is an Austronesian language of the Bima–Sumba subgroup spoken by a local community in eastern Indonesia.
  • 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_69a8862f7074819096afe7fe65e179e9 completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69abb0ba90e08190b990875d6e8e7e4a completed March 7, 2026, 4:59 a.m.
NED1 Entity disambiguation (via context triple) batch_69add1dd2d748190976277ac25f938ee completed March 8, 2026, 7:45 p.m.
NEDg Description generation batch_69add4628ed081908ea939b95e005299 completed March 8, 2026, 7:56 p.m.
NED2 Entity disambiguation (via description) batch_69add4e97dd08190a091d3d265b39138 completed March 8, 2026, 7:58 p.m.
Created at: March 4, 2026, 7:34 p.m.