Triple

T19510611
Position Surface form Disambiguated ID Type / Status
Subject Anu Komsi E488141 entity
Predicate name P16 FINISHED
Object Anu Komsi NE NERFINISHED

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: Anu Komsi | Statement: [Anu Komsi, name, Anu Komsi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Anu Komsi
Context triple: [Anu Komsi, name, Anu Komsi]
  • A. Anu Komsi chosen
    Anu Komsi is a Finnish soprano renowned for her versatile operatic and concert performances, particularly in contemporary and modern repertoire.
  • B. Kita Maninka
    Kita Maninka is a regional variety of the Manding language spoken primarily around the town of Kita in western Mali.
  • C. Yessica Kumala
    Yessica Kumala is an Indonesian-born former nightclub employee best known as the wife of American actor Josh Holloway.
  • D. Aurelia Fadilla
    Aurelia Fadilla was a Roman noblewoman of the 2nd century AD, known primarily as the daughter of Emperor Antoninus Pius and Empress Faustina the Elder.
  • E. Kali Ngrowo
    Kali Ngrowo is a significant river in East Java, Indonesia, known as one of the main waterways feeding the Brantas River system.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8e8da8bec819081f400199491ccc3 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e63516572c8190a8719c51fd3f7147 completed April 20, 2026, 2:15 p.m.
Created at: April 10, 2026, 1:40 p.m.