Triple

T9351446
Position Surface form Disambiguated ID Type / Status
Subject Phocas E225027 entity
Predicate spouse P13 FINISHED
Object Leontia E726487 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: Leontia | Statement: [Phocas, spouse, Leontia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Leontia
Context triple: [Phocas, spouse, Leontia]
  • A. Leontia chosen
    Leontia was a Byzantine imperial princess, the daughter of Emperor Leo I, known for her role in dynastic marriage alliances of the Eastern Roman Empire.
  • B. Tanaquil
    Tanaquil was a celebrated American ballerina and principal dancer with the New York City Ballet, renowned for her collaborations with George Balanchine in the mid-20th century.
  • C. Agathé
    Agathé is the ancient Greek name for the historic Mediterranean port city now known as Agde in southern France.
  • D. Theosebia
    Theosebia is a relatively obscure early Christian figure known primarily as a member of the family of Basil the Elder, associated with the influential Cappadocian Christian milieu.
  • E. Amphithea
    Amphithea is a figure in Greek mythology known primarily as the mother of Anticlea, who in turn is the mother of Odysseus.
  • 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_69ca842abfd48190949d71c3b86eeba8 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd4f93a9848190ad2ae24f2aa607d2 completed April 1, 2026, 5:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69d0e445c5308190be122215c92fd03d completed April 4, 2026, 10:13 a.m.
Created at: March 30, 2026, 7:41 p.m.