Triple

T32506948
Position Surface form Disambiguated ID Type / Status
Subject Pearl Sibshaw E830824 entity
Predicate relationshipToMarina P201421 FINISHED
Object suspicious of Marina's relationship with Howard 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: suspicious of Marina's relationship with Howard | Statement: [Pearl Sibshaw, relationshipToMarina, suspicious of Marina's relationship with Howard]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: relationshipToMarina
Context triple: [Pearl Sibshaw, relationshipToMarina, suspicious of Marina's relationship with Howard]
  • A. relationshipToMariner
    Indicates the specific familial, social, or professional connection that an entity has to a mariner.
  • B. hasRelationshipTypeWithMarina chosen
    Indicates that an entity has a specific type of relationship or connection with Marina.
  • C. relationshipToMaria
    Indicates the specific type of relationship or connection that an entity has to Maria.
  • D. relationshipToMariane
    Indicates the specific type of relationship or connection that an entity has to Mariane.
  • E. relationshipWithMarinaMniszech
    Indicates that an entity has a personal, political, or social relationship with Marina Mniszech.
  • 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_69f3492318348190ba37fb6b5f1d67f4 completed April 30, 2026, 12:20 p.m.
NER Named-entity recognition batch_6a037c894b488190bcbec2eccaff4a01 completed May 12, 2026, 7:16 p.m.
PD Predicate disambiguation batch_6a0379edf2d88190b492fca86ed23cac completed May 12, 2026, 7:05 p.m.
Created at: May 1, 2026, 1 a.m.