Triple
T33626107
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Groote Schuur Hospital |
E861409
|
entity |
| Predicate | hasDonorInFirstHeartTransplant |
P181465
|
FINISHED |
| Object | Denise Darvall |
—
|
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: Denise Darvall | Statement: [Groote Schuur Hospital, hasDonorInFirstHeartTransplant, Denise Darvall]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDonorInFirstHeartTransplant Context triple: [Groote Schuur Hospital, hasDonorInFirstHeartTransplant, Denise Darvall]
-
A.
donorOfTransplantedHeart
Indicates that one entity is the person who donated a heart that was transplanted into another entity.
-
B.
receivedBloodTransfusionFrom
Indicates that one entity has been given blood or blood products from another entity through a transfusion procedure.
-
C.
donorCellSpecies
Indicates the species from which the donor cell in a biological or experimental context originates.
-
D.
hasDonorModel
Indicates that an entity is associated with a specific donor model from which it is derived or based.
-
E.
donorCellSource
Indicates that one entity serves as the originating or contributing donor cell source for another entity or process.
- 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_69f34981c54c81909b33c3fa2208a52d |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f7764ab1fc81909f9348db87bd7692 |
completed | May 3, 2026, 4:22 p.m. |
| PD | Predicate disambiguation | batch_69f76905d9c88190b1ee810bc9ab644f |
completed | May 3, 2026, 3:25 p.m. |
| PDg | Predicate description generation | batch_69f77648979c8190b6cdbb835ab8987c |
completed | May 3, 2026, 4:22 p.m. |
Created at: May 1, 2026, 1:41 a.m.