Triple

T7514061
Position Surface form Disambiguated ID Type / Status
Subject House of Flanders E177594 entity
Predicate dynasticConnectionWith P44810 FINISHED
Object House of Normandy E104533 NE FINISHED

How this triple was built (3 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: House of Normandy | Statement: [House of Flanders, dynasticConnectionWith, House of Normandy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: House of Normandy
Context triple: [House of Flanders, dynasticConnectionWith, House of Normandy]
  • A. House of Normandy chosen
    The House of Normandy was a medieval European royal dynasty of Norman origin that ruled England and parts of France following the Norman Conquest of 1066.
  • B. House of Auvergne
    The House of Auvergne was a medieval French noble dynasty that held significant power and territories in the Auvergne region and produced influential counts and dukes.
  • C. House of Courtenay
    The House of Courtenay was a prominent medieval French noble family that produced Latin emperors of Constantinople and held significant influence in European aristocratic and crusader politics.
  • D. House of Blois
    The House of Blois was a powerful medieval French noble dynasty that produced influential counts, kings, and crusaders in France and England.
  • E. House of Rennes
    The House of Rennes was a medieval Breton noble dynasty that ruled the Duchy of Brittany and played a significant role in the politics of northwestern France.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: dynasticConnectionWith
Context triple: [House of Flanders, dynasticConnectionWith, House of Normandy]
  • A. dynasticInheritance
    Indicates that rights, titles, or property are passed down through a family line according to established rules of succession.
  • B. dynasticAlliance chosen
    Indicates a formal union or cooperative relationship established between ruling families or dynasties, typically through marriage or treaty, to secure mutual political or strategic advantage.
  • C. associatedWithDynasty
    Indicates that an entity has a historical, political, cultural, or familial connection to a specific dynasty.
  • D. isDynastic
    Indicates that a relationship, status, or succession is based on or belongs to a hereditary ruling family or lineage.
  • E. dynasticLegacy
    Indicates that a lineage, tradition, or influence is passed down through successive generations within a dynasty or family line.
  • F. None of above.

Provenance (4 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_69c69f2891148190a484f3b8222c6f1b completed March 27, 2026, 3:15 p.m.
NER Named-entity recognition batch_69c6f5d6ccb08190a568a9b58bfbd0cc completed March 27, 2026, 9:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69c84ef549588190ab950abb3678128f completed March 28, 2026, 9:58 p.m.
PD Predicate disambiguation batch_69c6f4d44e9481909813e073b194f6f4 completed March 27, 2026, 9:21 p.m.
Created at: March 27, 2026, 3:45 p.m.