Triple

T19599380
Position Surface form Disambiguated ID Type / Status
Subject Olonkho epic E470426 entity
Predicate featuresRealm P76995 FINISHED
Object Middle World 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: Middle World | Statement: [Olonkho epic, featuresRealm, Middle World]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Middle World
Context triple: [Olonkho epic, featuresRealm, Middle World]
  • A. Middle World chosen
    Middle World is the central earthly realm in Tengrism, where humans live between the upper spiritual heavens and the lower underworld.
  • B. Mid-World
    Mid-World is the decaying, post-apocalyptic fantasy realm that serves as the primary landscape for Stephen King’s The Dark Tower series, where magic, technology, and parallel realities intersect.
  • C. Viejo Mundo
    Viejo Mundo es el término histórico que designa a Europa, Asia y África en contraste con las tierras descubiertas posteriormente en el llamado Nuevo Mundo.
  • D. The Middle
    "The Middle" is a 2018 pop and electronic dance track by Zedd, Maren Morris, and Grey that became a major crossover hit and radio staple.
  • E. The Middle
    The Middle is an American sitcom that follows the everyday struggles and humor of a middle-class family living in the fictional town of Orson, Indiana.
  • 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_69e6407d46188190b9818665b2a698a5 completed April 20, 2026, 3:04 p.m.
Created at: April 10, 2026, 1:43 p.m.