Triple

T19595056
Position Surface form Disambiguated ID Type / Status
Subject Kaikesi E470329 entity
Predicate sibling P363 FINISHED
Object Raka 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: Raka | Statement: [Kaikesi, sibling, Raka]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Raka
Context triple: [Kaikesi, sibling, Raka]
  • A. Raka
    Raka is an individual known primarily through their personal relationship with Koki.
  • B. Raka
    Raka is a renowned Afrikaans narrative poem by N. P. van Wyk Louw that explores themes of civilization, barbarism, and moral conflict through an allegorical tale.
  • C. Rakau
    Rakau is a small rural settlement in Belarus located near the historical hill of Dziaržynskaja Hara, the country’s highest point.
  • D. Wulkuraka
    Wulkuraka is a suburban locality in the city of Ipswich, Queensland, Australia, known primarily as a residential area with rail infrastructure and access to nearby urban amenities.
  • E. Kurawa chosen
    Kurawa are the antagonistic royal cousins of the Pandawa in Javanese and broader Indonesian adaptations of the Mahabharata, often portrayed as embodiments of greed, envy, and tyranny.
  • 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_69d8e510024481908415c0d616fa6186 completed April 10, 2026, 11:54 a.m.
NER Named-entity recognition batch_69e640793cd88190b9b84491bfb2493f completed April 20, 2026, 3:04 p.m.
Created at: April 10, 2026, 1:43 p.m.