Triple

T222896
Position Surface form Disambiguated ID Type / Status
Subject Berber languages E4254 entity
Predicate hasLanguage P15 FINISHED
Object Shenwa
Shenwa is a Zenati Berber language spoken by a small community in the Chenoua (Shenwa) region of northern Algeria.
 E34075 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: Shenwa | Statement: [Berber languages, hasLanguage, Shenwa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Shenwa
Context triple: [Berber languages, hasLanguage, Shenwa]
  • A. Ahirani
    Ahirani is an Indo-Aryan dialect spoken primarily in the Khandesh region of Maharashtra, India, closely related to Marathi but with distinct phonological and lexical features.
  • B. Ebisu
    Ebisu is a fashionable Tokyo neighborhood known for its upscale dining, craft beer scene, and convenient access via Ebisu Station near Shibuya.
  • C. Shinsen
    Shinsen is a neighborhood in Tokyo’s Shibuya ward known for its residential streets, local eateries, and proximity to the bustling Shibuya Station area.
  • D. Tora
    Tora is a popular nickname for the Hanshin Tigers, a professional Japanese baseball team based in the Kansai region.
  • E. Kaiyukan
    Kaiyukan is a large, world-renowned public aquarium in Osaka, Japan, famous for its massive central tank and immersive marine life exhibits.
  • 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: Shenwa
Triple: [Berber languages, hasLanguage, Shenwa]
Generated description
Shenwa is a Zenati Berber language spoken by a small community in the Chenoua (Shenwa) region of northern Algeria.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Shenwa
Target entity description: Shenwa is a Zenati Berber language spoken by a small community in the Chenoua (Shenwa) region of northern Algeria.
  • A. Ahirani
    Ahirani is an Indo-Aryan dialect spoken primarily in the Khandesh region of Maharashtra, India, closely related to Marathi but with distinct phonological and lexical features.
  • B. Ebisu
    Ebisu is a fashionable Tokyo neighborhood known for its upscale dining, craft beer scene, and convenient access via Ebisu Station near Shibuya.
  • C. Shinsen
    Shinsen is a neighborhood in Tokyo’s Shibuya ward known for its residential streets, local eateries, and proximity to the bustling Shibuya Station area.
  • D. Tora
    Tora is a popular nickname for the Hanshin Tigers, a professional Japanese baseball team based in the Kansai region.
  • E. Kaiyukan
    Kaiyukan is a large, world-renowned public aquarium in Osaka, Japan, famous for its massive central tank and immersive marine life exhibits.
  • 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_69a2573508588190b522c2476d91acfe completed Feb. 28, 2026, 2:47 a.m.
NER Named-entity recognition batch_69a25c705fd88190bfee7f5e1f7cee17 completed Feb. 28, 2026, 3:09 a.m.
NED1 Entity disambiguation (via context triple) batch_69a386137da0819090249faf5127a5be completed March 1, 2026, 12:19 a.m.
NEDg Description generation batch_69a386ca1df08190a9b342fb75e3c6b4 completed March 1, 2026, 12:22 a.m.
NED2 Entity disambiguation (via description) batch_69a3870030a481909c413058525afcfd completed March 1, 2026, 12:23 a.m.
Created at: Feb. 28, 2026, 2:53 a.m.