Triple

T1871224
Position Surface form Disambiguated ID Type / Status
Subject Teda E39038 entity
Predicate language P15 FINISHED
Object Teda language E208969 NE FINISHED

How this triple was built (2 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: [Teda, language, Teda language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Teda language
Context triple: [Teda, language, Teda language]
  • A. Teda language chosen
    The Teda language is a Saharan language spoken primarily by the Teda (northern Toubou) people of the Tibesti region in Chad and southern Libya.
  • B. Logba language
    The Logba language is a Niger-Congo language spoken by the Logba people of southeastern Ghana.
  • C. Teso language
    Teso language is an Eastern Nilotic language spoken primarily by the Iteso people in eastern Uganda and western Kenya.
  • D. Kaado language
    The Kaado language is a regional variety within the Songhay language family spoken by communities in parts of West Africa.
  • E. 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.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69addf5419488190ad96110f6ac7111f completed March 8, 2026, 8:43 p.m.
Created at: March 4, 2026, 7:34 p.m.