Triple

T35190013
Position Surface form Disambiguated ID Type / Status
Subject Henrik Vanger E1016094 entity
Predicate commissionedInvestigation P182370 FINISHED
Object disappearance of Harriet Vanger 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: disappearance of Harriet Vanger | Statement: [Henrik Vanger, commissionedInvestigation, disappearance of Harriet Vanger]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: commissionedInvestigation
Context triple: [Henrik Vanger, commissionedInvestigation, disappearance of Harriet Vanger]
  • A. commissionInvestigated
    Indicates that a commission formally examined, inquired into, or investigated a particular matter or entity.
  • B. governmentInvestigation
    Indicates that a government authority is formally examining or probing an entity, event, or activity to gather facts, determine compliance, or assess potential wrongdoing.
  • C. investigatedBy
    Indicates that an entity is the subject of an investigation carried out by another entity.
  • D. oversawInvestigationOf
    Indicates that one entity had supervisory or managerial responsibility for conducting or directing an investigation concerning another entity.
  • E. investigate
    Indicates that one entity systematically examines, studies, or inquires into another entity or situation to uncover facts or gain understanding.
  • F. None of above. chosen

Provenance (4 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_69f76ddd815c8190b822eea06630f9fb completed May 3, 2026, 3:46 p.m.
NER Named-entity recognition batch_69f78dc57dac81908b5aa4957ca02bd2 completed May 3, 2026, 6:02 p.m.
PD Predicate disambiguation batch_69f78b9106008190930b3b3675b737d6 completed May 3, 2026, 5:53 p.m.
PDg Predicate description generation batch_69f78c337cec8190bfdab225a3cc96db completed May 3, 2026, 5:56 p.m.
Created at: May 3, 2026, 4:02 p.m.