Triple

T13852616
Position Surface form Disambiguated ID Type / Status
Subject Samantha Gwendoline Sheffield E332980 entity
Predicate hasGivenPublicInterviewsOn P76434 FINISHED
Object family life at 10 Downing Street 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: family life at 10 Downing Street | Statement: [Samantha Gwendoline Sheffield, hasGivenPublicInterviewsOn, family life at 10 Downing Street]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasGivenPublicInterviewsOn
Context triple: [Samantha Gwendoline Sheffield, hasGivenPublicInterviewsOn, family life at 10 Downing Street]
  • A. hasGivenInterviewsIn
    Indicates that an entity has conducted or participated in interviews within a specified place or context.
  • B. gaveInterviewsAbout chosen
    Indicates that an entity conducted interviews whose subject or topic was another specified entity.
  • C. hasGivenNumberOfInterviewsAbout
    Indicates that an entity has conducted or participated in a specified number of interviews concerning another entity or topic.
  • D. hasInterviews
    Indicates that one entity conducts, contains, or is associated with interviews involving another entity.
  • E. usesInterviews
    Indicates that one entity employs interviews as a method or tool in relation to another entity or process.
  • 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_69d81c5ba13c8190839315f54768acfd completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de02da9460819093a3ec5a3c62ea81 completed April 14, 2026, 9:03 a.m.
PD Predicate disambiguation batch_69dbc8691b608190a25a7c70a366b170 completed April 12, 2026, 4:29 p.m.
Created at: April 9, 2026, 10:14 p.m.