Triple
T25609823
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2020 Alexei Navalny poisoning |
E642016
|
entity |
| Predicate | locationHospitalizationSubsequent |
P22425
|
FINISHED |
| Object | Charité – Universitätsmedizin Berlin |
—
|
NE NERFINISHED |
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: Charité – Universitätsmedizin Berlin | Statement: [2020 Alexei Navalny poisoning, locationHospitalizationSubsequent, Charité – Universitätsmedizin Berlin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locationHospitalizationSubsequent Context triple: [2020 Alexei Navalny poisoning, locationHospitalizationSubsequent, Charité – Universitätsmedizin Berlin]
-
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.
hospitalServicesTransferredTo
Indicates that responsibility for providing hospital services has been moved from one entity to another.
-
D.
laterAdmitted
Indicates that an entity acknowledged, confessed, or accepted something as true at a subsequent time after an earlier event or statement.
-
E.
hospitalizedFor
Indicates that an entity is admitted to and staying in a medical facility specifically due to a particular illness, condition, or medical reason.
- 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_69e75dc6ccf081908d49578fd36a76d5 |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f78fd5a6388190bfda4bbb2e222e5b |
completed | May 3, 2026, 6:11 p.m. |
| PD | Predicate disambiguation | batch_69f78e2ac3fc819081a45c6841375c8d |
completed | May 3, 2026, 6:04 p.m. |
Created at: April 21, 2026, 4:40 p.m.