Triple
T4174265
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | North Brother Island |
E86437
|
entity |
| Predicate | hospitalFunction |
P54215
|
FINISHED |
| Object | quarantine for smallpox |
—
|
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: quarantine for smallpox | Statement: [North Brother Island, hospitalFunction, quarantine for smallpox]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hospitalFunction Context triple: [North Brother Island, hospitalFunction, quarantine for smallpox]
-
A.
healthSystem
Indicates a relationship where an entity functions as, belongs to, or is managed within a particular health care system or network.
-
B.
containsHospital
Indicates that one entity includes or encompasses a hospital within its boundaries or composition.
-
C.
hospitalizedIn
Indicates that a person or patient is admitted for medical care and staying as an inpatient in a specified hospital or healthcare facility.
-
D.
hasHospitalType
Indicates that a hospital is classified as belonging to a specific type or category (e.g., general, specialized, teaching).
-
E.
majorHospital
Indicates that a hospital holds a primary or leading status within a healthcare system or region, typically due to its size, capacity, or range of services.
- 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_69aed93de98c8190ad838ce507b77c8a |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69af07078cb081909f64326b12522410 |
completed | March 9, 2026, 5:44 p.m. |
| PD | Predicate disambiguation | batch_69af019155448190b19868583272513f |
completed | March 9, 2026, 5:21 p.m. |
| PDg | Predicate description generation | batch_69af07059d288190a1ea79449414fbce |
completed | March 9, 2026, 5:44 p.m. |
Created at: March 9, 2026, 3:45 p.m.