Triple

T13352068
Position Surface form Disambiguated ID Type / Status
Subject Medivh E318092 entity
Predicate apprentice P41095 FINISHED
Object Khadgar E932339 NE FINISHED

How this triple was built (3 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: Khadgar | Statement: [Medivh, apprentice, Khadgar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Khadgar
Context triple: [Medivh, apprentice, Khadgar]
  • A. Khadgar chosen
    Khadgar is a powerful human archmage from the Warcraft universe, renowned for his pivotal role in major events such as the fight against the Burning Legion and the defense of Azeroth.
  • B. Algrim
    Algrim is a powerful Dark Elf warrior from the Marvel Comics universe who becomes the monstrous Kurse after being transformed to serve as a formidable foe of Thor.
  • C. Raskhan
    Raskhan was a 16th–17th century Indian poet and devotee of Krishna, renowned for his lyrical Braj Bhasha compositions celebrating bhakti (devotional love).
  • D. Tyrael
    Tyrael is an archangel and central heroic figure in Blizzard's Diablo video game series, known for defying the High Heavens to aid humanity against the forces of Hell.
  • E. Unseld
    Unseld is the surname most famously associated with Wes Unseld, a Hall of Fame American basketball player and coach known for his rebounding and outlet passing.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: apprentice
Context triple: [Medivh, apprentice, Khadgar]
  • A. trainedAs
    Indicates that one entity has received education or instruction to perform the role, profession, or function represented by another entity.
  • B. offersApprenticeshipTraining
    Indicates that one entity provides apprenticeship-based training opportunities or programs to another entity.
  • C. trainer chosen
    Indicates a relationship where one entity teaches, coaches, or prepares another entity to develop skills, knowledge, or performance in a particular domain.
  • D. applicant
    Indicates that an entity plays the role of a person or organization formally applying for something (such as a job, program, or permit) from another entity.
  • E. occupationBegan
    Indicates the point in time when an entity started holding a particular occupation or job.
  • F. None of above.

Provenance (4 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_69d806b5a3c08190b42c267fb092f98a completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d99e8c2f1c819094f0970f35f18afa completed April 11, 2026, 1:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7397b871c819081272c48b3210e00 completed May 3, 2026, 12:03 p.m.
PD Predicate disambiguation batch_69d98f6fd8bc819086dddb6f376efa57 completed April 11, 2026, 12:01 a.m.
Created at: April 9, 2026, 9:32 p.m.