Triple

T7825091
Position Surface form Disambiguated ID Type / Status
Subject Kejiahua E181225 entity
Predicate hasDialect P4251 FINISHED
Object Hailu Hakka E181220 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: Hailu Hakka | Statement: [Kejiahua, hasDialect, Hailu Hakka]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hailu Hakka
Context triple: [Kejiahua, hasDialect, Hailu Hakka]
  • A. Hailu Hakka chosen
    Hailu Hakka is a major regional variety of the Hakka Chinese language, spoken primarily in parts of Guangdong and neighboring areas and known for its distinctive phonology and vocabulary.
  • B. Menan Asfaw
    Menan Asfaw was the Empress consort of Ethiopia as the wife of Emperor Haile Selassie I.
  • C. Sidamu Afoo
    Sidamu Afoo is the Cushitic language spoken by the Sidama people of southern Ethiopia.
  • D. Jantirar Asfaw
    Jantirar Asfaw was an Ethiopian nobleman and regional ruler best known as the father of Empress Menen Asfaw, consort of Emperor Haile Selassie I.
  • E. Lebna Dengel
    Lebna Dengel was an early 16th-century emperor of Ethiopia known for his struggles against Muslim invasions and for initiating contact with Portugal in search of military support.
  • 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_69ca8282ccec819083c48efb72d21cf9 completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cafa0c1f5c8190b16db20daad159a1 completed March 30, 2026, 10:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69cc55eedb9881908aeb6d3276b31b6c completed March 31, 2026, 11:17 p.m.
Created at: March 30, 2026, 4:42 p.m.