Triple

T37333910
Position Surface form Disambiguated ID Type / Status
Subject Aulus Cornelius Sulla E926829 entity
Predicate possibleKinship P42547 FINISHED
Object kinsman of Lucius Cornelius Sulla 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: kinsman of Lucius Cornelius Sulla | Statement: [Aulus Cornelius Sulla, possibleKinship, kinsman of Lucius Cornelius Sulla]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: possibleKinship
Context triple: [Aulus Cornelius Sulla, possibleKinship, kinsman of Lucius Cornelius Sulla]
  • A. possibleFamily
    Indicates that two entities could plausibly be related as members of the same family, though the familial relationship is not confirmed.
  • B. usesKinshipSystem
    Indicates that one entity organizes or interprets familial relationships according to the kinship classification system associated with another entity.
  • C. possibleRelative chosen
    Indicates a relationship where one entity may be related to another by family or kinship, but the exact nature of the relationship is uncertain or not fully established.
  • D. hasFamilialTieTo
    Indicates a relationship where two entities are connected by family bonds, such as by blood, marriage, or adoption.
  • E. certaintyOfRelationships
    Indicates the degree of confidence or assurance that specified relationships between entities are correct or valid.
  • 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_69f76eb4e8a881908bd40da28f36fc7e completed May 3, 2026, 3:50 p.m.
NER Named-entity recognition batch_69fb9e1845e881908d19158440cf3b87 completed May 6, 2026, 8:01 p.m.
PD Predicate disambiguation batch_69fb8d08d6988190a00794ac26078348 completed May 6, 2026, 6:48 p.m.
Created at: May 3, 2026, 4:16 p.m.