Triple

T15944801
Position Surface form Disambiguated ID Type / Status
Subject North Omotic E386656 entity
Predicate hasLanguage P15 FINISHED
Object Bench language E347535 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: Bench language | Statement: [North Omotic, hasLanguage, Bench language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bench language
Context triple: [North Omotic, hasLanguage, Bench language]
  • A. Bench language chosen
    Bench language is an Afro-Asiatic Omotic language spoken by the Bench people of southwestern Ethiopia.
  • B. Bicep language
    Bicep language is a domain-specific, declarative language developed by Microsoft for authoring Azure infrastructure-as-code templates more simply and reliably than traditional JSON-based ARM templates.
  • C. Pear language
    Pear language is an Austroasiatic language of the Pearic branch spoken by the Pear people of Cambodia and considered highly endangered.
  • D. Bo language
    Bo language is an extinct Great Andamanese language once spoken by the Bo people of the Andaman Islands in India.
  • E. Beta (programming language)
    Beta is an object-oriented programming language developed as a successor to Simula, notable for its unification of classes and procedures into a single abstraction called patterns.
  • 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_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.
Created at: April 10, 2026, 4:53 a.m.