Triple

T3298855
Position Surface form Disambiguated ID Type / Status
Subject Geʽez script E69281 entity
Predicate usedForLanguage P907 FINISHED
Object Bench language
Bench language is an Afro-Asiatic Omotic language spoken by the Bench people of southwestern Ethiopia.
 E347535 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: Bench language | Statement: [Geʽez script, usedForLanguage, Bench language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Bench language
Context triple: [Geʽez script, usedForLanguage, Bench language]
  • A. Bo language
    Bo language is an extinct Great Andamanese language once spoken by the Bo people of the Andaman Islands in India.
  • B. Alur language
    The Alur language is a Western Nilotic language spoken primarily by the Alur people of northwestern Uganda and northeastern Democratic Republic of the Congo.
  • C. Mono language
    Mono language is a Native American Uto-Aztecan language traditionally spoken by the Mono people of eastern California.
  • D. B programming language
    The B programming language is an early, minimalist high-level language developed at Bell Labs that directly influenced the design of the C programming language.
  • E. Bunun language
    The Bunun language is an Austronesian language spoken by the Bunun indigenous people of central and southern Taiwan, known for its complex verb morphology and rich oral traditions.
  • 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: Bench language
Triple: [Geʽez script, usedForLanguage, Bench language]
Generated description
Bench language is an Afro-Asiatic Omotic language spoken by the Bench people of southwestern Ethiopia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Bench language
Target entity description: Bench language is an Afro-Asiatic Omotic language spoken by the Bench people of southwestern Ethiopia.
  • A. Bo language
    Bo language is an extinct Great Andamanese language once spoken by the Bo people of the Andaman Islands in India.
  • B. Alur language
    The Alur language is a Western Nilotic language spoken primarily by the Alur people of northwestern Uganda and northeastern Democratic Republic of the Congo.
  • C. Mono language
    Mono language is a Native American Uto-Aztecan language traditionally spoken by the Mono people of eastern California.
  • D. B programming language
    The B programming language is an early, minimalist high-level language developed at Bell Labs that directly influenced the design of the C programming language.
  • E. Bunun language
    The Bunun language is an Austronesian language spoken by the Bunun indigenous people of central and southern Taiwan, known for its complex verb morphology and rich oral traditions.
  • 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_69ad859e529c8190a404273f53cb487d completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb0a49b748190b6db99a85c3cb3c5 completed March 8, 2026, 5:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69b2f3d759908190b1f5170930ff03c5 completed March 12, 2026, 5:11 p.m.
NEDg Description generation batch_69b2f9ec098c8190aaa763d7b9c5cceb completed March 12, 2026, 5:37 p.m.
NED2 Entity disambiguation (via description) batch_69b316408090819090a4792b3d5185f0 completed March 12, 2026, 7:38 p.m.
Created at: March 8, 2026, 3:11 p.m.