Triple

T1291474
Position Surface form Disambiguated ID Type / Status
Subject Carnegie family E27556 entity
Predicate hasSurnameCategory P17126 FINISHED
Object Scottish surnames 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: Scottish surnames | Statement: [Carnegie family, hasSurnameCategory, Scottish surnames]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasSurnameCategory
Context triple: [Carnegie family, hasSurnameCategory, Scottish surnames]
  • A. familyNameCategory chosen
    Indicates that an entity is associated with a particular classification or grouping based on its family name.
  • B. hasMarriedSurname
    Indicates that a person’s current surname is the one they adopted through marriage.
  • C. isMatronymicOf
    Indicates that one entity is a name or designation derived from the mother of another entity, typically used as that entity’s family or identifying name.
  • D. usedWithSurname
    Indicates that something (typically a given name or title) is used together with a particular surname in naming or reference.
  • E. familyName
    Indicates that one entity is the family (last) name associated with another entity (typically a person).
  • 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_69a496d4ec448190ad653b2590c46711 completed March 1, 2026, 7:43 p.m.
NER Named-entity recognition batch_69a4c0d7d15081909d3af19b9297f1cc completed March 1, 2026, 10:42 p.m.
PD Predicate disambiguation batch_69a4bee41ca08190b0ad6f7ea40c0b62 completed March 1, 2026, 10:34 p.m.
Created at: March 1, 2026, 7:51 p.m.