Triple

T10367923
Position Surface form Disambiguated ID Type / Status
Subject Dirty Pretty Things E244302 entity
Predicate language P15 FINISHED
Object Somali E41110 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: Somali | Statement: [Dirty Pretty Things, language, Somali]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Somali
Context triple: [Dirty Pretty Things, language, Somali]
  • A. Somali chosen
    Somali is a Cushitic language spoken primarily in Somalia and neighboring regions of the Horn of Africa, serving as a major lingua franca and national language for the Somali people.
  • B. Somali somalo
    The Somali somalo was the former official currency of Somalia used before the adoption of the Somali shilling.
  • C. Afar language
    The Afar language is a Cushitic language spoken primarily by the Afar people in Ethiopia, Eritrea, and Djibouti.
  • D. Afaan Orma
    Afaan Orma is the native language of the Orma people, a Cushitic-speaking community primarily found in Kenya.
  • E. Benadiri Somali
    Benadiri Somali is a coastal dialect of the Somali language spoken primarily by communities in and around Mogadishu and along Somalia’s southern Benadir coast.
  • 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_69d381b3e328819094b23b8edcd29b5a completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4e97106448190a075948e63184f47 completed April 7, 2026, 11:24 a.m.
NED1 Entity disambiguation (via context triple) batch_69d79546b078819089dec7628c95a681 completed April 9, 2026, 12:02 p.m.
Created at: April 6, 2026, noon