Triple

T20973290
Position Surface form Disambiguated ID Type / Status
Subject Duchess of Savoy E516555 entity
Predicate typicalAcquisition P13368 FINISHED
Object marriage to the Duke of Savoy LITERAL 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: marriage to the Duke of Savoy | Statement: [Duchess of Savoy, typicalAcquisition, marriage to the Duke of Savoy]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: typicalAcquisition
Context triple: [Duchess of Savoy, typicalAcquisition, marriage to the Duke of Savoy]
  • A. acquisitionType
    Indicates the specific kind or category of acquisition relationship that exists between entities (such as a company buying another company, assets, or a controlling stake).
  • B. acquisition
    Indicates the act or relationship in which one entity obtains ownership or control of another entity, asset, or resource.
  • C. acquisitionPattern chosen
    Indicates the characteristic way in which one entity acquires or obtains another entity or resource, such as the method, frequency, or structure of the acquisition.
  • D. acquisitionCategory
    Indicates the type or classification of an acquisition associated with an entity or transaction.
  • E. acquisitionTarget
    Indicates that one entity is the intended or actual company or asset being acquired by another in a merger or acquisition transaction.
  • F. None of above.

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_69e0b4fee5ac8190875fa9ceba1a5e5e completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6fba2406c8190bd75dec585c14bfa completed April 21, 2026, 4:22 a.m.
PD Predicate disambiguation batch_69e5dbe6976081908abd4e9c8734bae9 completed April 20, 2026, 7:55 a.m.
Created at: April 16, 2026, 1:45 p.m.