Triple

T15944792
Position Surface form Disambiguated ID Type / Status
Subject North Omotic E386656 entity
Predicate hasSubgroup P747 FINISHED
Object Gonga
Gonga is a subgroup of the North Omotic branch of the Afroasiatic language family, comprising several closely related languages spoken in southwestern Ethiopia.
 E1185204 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: Gonga | Statement: [North Omotic, hasSubgroup, Gonga]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Gonga
Context triple: [North Omotic, hasSubgroup, Gonga]
  • A. Gongnie
    Gongnie was the personal name of King You of Zhou, the last king of the Western Zhou dynasty in ancient China.
  • B. Gogango
    Gogango is a small rural locality in Central Queensland, Australia, situated west of Rockhampton and known for cattle grazing and its position along the Capricorn Highway and Fitzroy River.
  • C. Sanchica
    Sanchica is the fictional daughter of Sancho Panza in Miguel de Cervantes' novel "Don Quixote."
  • D. Ganguise
    Ganguise is a watercourse in southern France that feeds the artificial reservoir known as Lac de la Ganguise.
  • E. Taongi
    Taongi is a remote, uninhabited coral atoll in the Marshall Islands known for its rich marine biodiversity and relatively undisturbed natural environment.
  • 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: Gonga
Triple: [North Omotic, hasSubgroup, Gonga]
Generated description
Gonga is a subgroup of the North Omotic branch of the Afroasiatic language family, comprising several closely related languages spoken in southwestern Ethiopia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Gonga
Target entity description: Gonga is a subgroup of the North Omotic branch of the Afroasiatic language family, comprising several closely related languages spoken in southwestern Ethiopia.
  • A. Gongnie
    Gongnie was the personal name of King You of Zhou, the last king of the Western Zhou dynasty in ancient China.
  • B. Gogango
    Gogango is a small rural locality in Central Queensland, Australia, situated west of Rockhampton and known for cattle grazing and its position along the Capricorn Highway and Fitzroy River.
  • C. Sanchica
    Sanchica is the fictional daughter of Sancho Panza in Miguel de Cervantes' novel "Don Quixote."
  • D. Ganguise
    Ganguise is a watercourse in southern France that feeds the artificial reservoir known as Lac de la Ganguise.
  • E. Taongi
    Taongi is a remote, uninhabited coral atoll in the Marshall Islands known for its rich marine biodiversity and relatively undisturbed natural environment.
  • 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_69d86da882448190a82ea962fe343b79 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e156d016588190ae368197dfa7d43a completed April 16, 2026, 9:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffb5beabbc8190977f14c1b3ccdf29 completed May 9, 2026, 10:31 p.m.
NEDg Description generation batch_69ffb677927c8190bd45e7bae5fcf1ed completed May 9, 2026, 10:34 p.m.
NED2 Entity disambiguation (via description) batch_69ffb7468fb88190a56cf1df5bd20f63 completed May 9, 2026, 10:37 p.m.
Created at: April 10, 2026, 4:53 a.m.