Triple

T376196
Position Surface form Disambiguated ID Type / Status
Subject Gabon E8377 entity
Predicate nationalLanguage P236 FINISHED
Object Punu
Punu is a Bantu language spoken primarily by the Punu people of southern Gabon and neighboring regions.
E48945 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: Punu | Statement: [Gabon, nationalLanguage, Punu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Punu
Context triple: [Gabon, nationalLanguage, Punu]
  • A. Lapa
    Lapa is a historic and bohemian neighborhood in Rio de Janeiro, Brazil, famous for its vibrant nightlife, samba clubs, and iconic aqueduct arches.
  • B. Combarbalá
    Combarbalá is a small Chilean town and municipality in the Coquimbo Region, known for its semi-arid landscapes, goat farming, and distinctive combarbalite stone crafts.
  • C. Sibaté
    Sibaté is a municipality in central Colombia known for its agricultural production and proximity to Bogotá within the Cundinamarca Department.
  • D. Idumea
    Idumea was an ancient region south of Judea, inhabited by the Edomites and later integrated into the Hasmonean and Herodian Jewish realms.
  • E. Nasar
    Nasar is a surname most notably associated with Sylvia Nasar, the economist and author of "A Beautiful Mind."
  • 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: Punu
Triple: [Gabon, nationalLanguage, Punu]
Generated description
Punu is a Bantu language spoken primarily by the Punu people of southern Gabon and neighboring regions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Punu
Target entity description: Punu is a Bantu language spoken primarily by the Punu people of southern Gabon and neighboring regions.
  • A. Lapa
    Lapa is a historic and bohemian neighborhood in Rio de Janeiro, Brazil, famous for its vibrant nightlife, samba clubs, and iconic aqueduct arches.
  • B. Combarbalá
    Combarbalá is a small Chilean town and municipality in the Coquimbo Region, known for its semi-arid landscapes, goat farming, and distinctive combarbalite stone crafts.
  • C. Sibaté
    Sibaté is a municipality in central Colombia known for its agricultural production and proximity to Bogotá within the Cundinamarca Department.
  • D. Canela
    Canela is a coastal rural municipality in Chile’s Coquimbo Region, known for its small agricultural communities and semi-arid landscapes.
  • E. Idumea
    Idumea was an ancient region south of Judea, inhabited by the Edomites and later integrated into the Hasmonean and Herodian Jewish realms.
  • 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_69a2e7f2ec648190b42bc7db424f8109 completed Feb. 28, 2026, 1:04 p.m.
NER Named-entity recognition batch_69a2ec169a848190a577aa093c878839 completed Feb. 28, 2026, 1:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69a3fe90edc48190a477971920c60918 completed March 1, 2026, 8:53 a.m.
NEDg Description generation batch_69a3fef7fd748190b92b9979a76fcbb4 completed March 1, 2026, 8:55 a.m.
NED2 Entity disambiguation (via description) batch_69a4003d118081908aabb8458ddf5982 completed March 1, 2026, 9 a.m.
Created at: Feb. 28, 2026, 1:08 p.m.