Triple

T22388674
Position Surface form Disambiguated ID Type / Status
Subject Gary Heidnik E553459 entity
Predicate psychiatricHospitalization P22425 FINISHED
Object committed to mental institutions multiple times 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: committed to mental institutions multiple times | Statement: [Gary Heidnik, psychiatricHospitalization, committed to mental institutions multiple times]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: psychiatricHospitalization
Context triple: [Gary Heidnik, psychiatricHospitalization, committed to mental institutions multiple times]
  • A. hospitalizedIn chosen
    Indicates that a person or patient is admitted for medical care and staying as an inpatient in a specified hospital or healthcare facility.
  • B. containsHospital
    Indicates that one entity includes or encompasses a hospital within its boundaries or composition.
  • C. numberOfHospitalized
    Indicates the count of individuals who have been admitted to a hospital for medical care.
  • D. hasPsychologicalCondition
    Indicates that an entity experiences or is diagnosed with a particular psychological or mental health condition.
  • E. requiresQualifyingHospitalStayFor
    Indicates that one entity must have a prior qualifying hospital stay as a prerequisite condition for another entity (such as a service, benefit, or coverage) to apply.
  • 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_69e11e4cf87c8190a1ff474daec326b7 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15858c13c819098fe66a50ecea7d7 completed April 29, 2026, 1:01 a.m.
PD Predicate disambiguation batch_69e73015484c8190a9a0b9f554b61a81 completed April 21, 2026, 8:06 a.m.
Created at: April 16, 2026, 8:45 p.m.