Triple

T2511744
Position Surface form Disambiguated ID Type / Status
Subject Septimius Severus E52716 entity
Predicate coEmperorWith P10356 FINISHED
Object Geta E216966 NE FINISHED

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: Geta | Statement: [Septimius Severus, coEmperorWith, Geta]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Geta
Context triple: [Septimius Severus, coEmperorWith, Geta]
  • A. Geta chosen
    Geta was a short-reigning Roman emperor of the Severan dynasty, known for his joint rule and bitter rivalry with his brother Caracalla, who ultimately had him murdered.
  • B. Usa Jingū
    Usa Jingū is a prominent Shinto shrine in Ōita Prefecture, Japan, revered as the principal sanctuary of the war and guardian deity Hachiman and a historically important religious center.
  • C. Takamikura
    Takamikura is the ornate imperial throne used in Kyoto for the enthronement ceremonies of Japanese emperors.
  • D. Marichi
    Marichi is a revered Vedic sage (one of the Saptarishi) regarded as a mind-born son of Brahma and an important progenitor in Hindu cosmology.
  • E. Jōkō
    Jōkō is the Japanese honorific title traditionally given to a retired emperor who has abdicated the throne.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69ab4958e76481908a235377dd921c9e completed March 6, 2026, 9:38 p.m.
NER Named-entity recognition batch_69abd1efb5c48190a9b47b39a388412b completed March 7, 2026, 7:21 a.m.
NED1 Entity disambiguation (via context triple) batch_69af2b934d3c81909627a5f4d6e6ca6a completed March 9, 2026, 8:20 p.m.
Created at: March 6, 2026, 9:46 p.m.