Triple

T20999971
Position Surface form Disambiguated ID Type / Status
Subject Fulk II of Anjou E517258 entity
Predicate mother P120 FINISHED
Object Roscille of Loches 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: Roscille of Loches | Statement: [Fulk II of Anjou, mother, Roscille of Loches]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Roscille of Loches
Context triple: [Fulk II of Anjou, mother, Roscille of Loches]
  • A. Roscille of Loches chosen
    Roscille of Loches was a noblewoman of early medieval France, best known as a countess of Anjou and influential member of the Angevin ruling family.
  • B. Aelinde of Amboise
    Aelinde of Amboise was a medieval noblewoman known primarily as the wife of Ingelger, the founder of the House of Anjou.
  • C. Radegonde of France
    Radegonde of France was a French princess of the 15th century, known primarily as a daughter of King Charles VII of France.
  • D. Ema of Aquitaine
    Ema of Aquitaine was a medieval noblewoman of the ducal House of Aquitaine, known primarily as a daughter of William IX, Duke of Aquitaine.
  • E. Bertha of Rouergue
    Bertha of Rouergue was an 11th-century French noblewoman and heiress whose marriage helped transfer the County of Rouergue into the sphere of the Counts of Barcelona.
  • 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_69e0b5006e2881909fc2383f841740cc completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e6fc24a6dc8190a6bf81cf1d9590c0 completed April 21, 2026, 4:25 a.m.
Created at: April 16, 2026, 1:51 p.m.