Triple

T8396009
Position Surface form Disambiguated ID Type / Status
Subject Holy Roman Empress E198052 entity
Predicate notableOfficeHolder P5750 FINISHED
Object Theophanu E235129 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: Theophanu | Statement: [Holy Roman Empress, notableOfficeHolder, Theophanu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Theophanu
Context triple: [Holy Roman Empress, notableOfficeHolder, Theophanu]
  • A. Theophanu chosen
    Theophanu was a Byzantine-born empress of the Holy Roman Empire who played a crucial political role in the late 10th century as the wife of Emperor Otto II and regent for their son Otto III.
  • B. Maria of Amnia
    Maria of Amnia was a Byzantine empress consort of Emperor Constantine VI, noted for her role in the political and dynastic struggles of the late 8th century.
  • C. Verina
    Verina was a 5th-century Byzantine empress and influential political figure, wife of Emperor Leo I and mother-in-law of Emperor Zeno.
  • D. Kunegunda
    Kunegunda is a feminine given name of Polish origin, historically borne by European nobility such as Theresa Kunegunda Sobieska.
  • E. Helena of Hungary
    Helena of Hungary was a medieval Hungarian princess who became Duchess of Austria through her marriage to Leopold V.
  • 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_69ca82f816bc8190ab321c07d72208c1 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb81874d6c8190bbc0ac832d8a339d completed March 31, 2026, 8:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69ce6cdb3b48819091c554539e74812a completed April 2, 2026, 1:19 p.m.
Created at: March 30, 2026, 6:04 p.m.