Triple

T16776117
Position Surface form Disambiguated ID Type / Status
Subject Leo IV the Khazar E407727 entity
Predicate regnalName P744 FINISHED
Object Leo IV 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: Leo IV | Statement: [Leo IV the Khazar, regnalName, Leo IV]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Leo IV
Context triple: [Leo IV the Khazar, regnalName, Leo IV]
  • A. Leo IV the Khazar chosen
    Leo IV the Khazar was a Byzantine emperor of the Isaurian dynasty who ruled in the late 8th century and continued the iconoclast policies of his predecessors.
  • B. Leo III
    Leo III is the live lion mascot that represents the University of North Alabama at its athletic events and campus activities.
  • C. Leo III the Isaurian
    Leo III the Isaurian was an 8th-century Byzantine emperor best known for initiating the first phase of Byzantine Iconoclasm and stabilizing the empire against external threats.
  • D. Leo V
    Leo V was a 14th-century King of the Armenian Kingdom of Cilicia, known for his efforts to defend his realm against Mamluk invasions and for being its last ruling monarch.
  • E. Leo V the Armenian
    Leo V the Armenian was a 9th-century Byzantine emperor best known for restoring and enforcing iconoclasm within the empire.
  • 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_69d8839270588190886720d9519bbf8f completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3b039a2a88190865e6a42c830c54d completed April 18, 2026, 4:24 p.m.
Created at: April 10, 2026, 5:22 a.m.