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.