Triple

T4076769
Position Surface form Disambiguated ID Type / Status
Subject Tulu E86782 entity
Predicate closelyRelatedTo P37 FINISHED
Object Kodava E169791 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: Kodava | Statement: [Tulu, closelyRelatedTo, Kodava]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kodava
Context triple: [Tulu, closelyRelatedTo, Kodava]
  • A. Kodava chosen
    Kodava is a Dravidian language spoken primarily by the Kodava (Coorg) community in the Kodagu district of Karnataka, India.
  • B. Kauhava
    Kauhava is a town in western Finland known historically for its aviation activities and air base, as well as its traditional knife-making heritage.
  • C. Karinska
    Karinska was a renowned 20th-century costume designer best known for her influential work in ballet and theater, particularly with the New York City Ballet.
  • D. Riasti
    Riasti is a regional dialect of the Saraiki language spoken primarily in parts of southern Punjab, Pakistan.
  • E. Paltamo
    Paltamo is a small municipality in the Kainuu region of Finland, known as the birthplace of the national poet Eino Leino.
  • 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_69aed93ebe448190a1f1686e28740ac9 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aefc4ba3f08190a6c6aaf6e9c99bd5 completed March 9, 2026, 4:58 p.m.
NED1 Entity disambiguation (via context triple) batch_69b562bea9b48190bcd1396c0cb19697 completed March 14, 2026, 1:29 p.m.
Created at: March 9, 2026, 3:39 p.m.