Triple
T38641247
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | trapped neutrophil syndrome |
E938598
|
entity |
| Predicate | diseaseLocation |
P63668
|
FINISHED |
| Object | bone marrow |
—
|
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: bone marrow | Statement: [trapped neutrophil syndrome, diseaseLocation, bone marrow]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: diseaseLocation Context triple: [trapped neutrophil syndrome, diseaseLocation, bone marrow]
-
A.
affectsAnatomicalLocation
chosen
Indicates that one entity produces an effect on, or has an impact at, a specific anatomical location.
-
B.
involvedLocation
Indicates that an event, action, or relationship takes place in, or is significantly associated with, a particular location.
-
C.
diseaseAffects
Indicates that a disease has a harmful impact on, or produces pathological changes in, a specified entity.
-
D.
diseaseContext
Indicates that the relationship or action occurs within, is influenced by, or is specifically relevant to a particular disease or pathological condition.
-
E.
diseaseType
Indicates that one entity is classified as a specific type or category of disease in relation to another entity.
- 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_69f76ed948ec81908ce7811608a8f359 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fcdb0de8c08190928cd1323f80ab5c |
completed | May 7, 2026, 6:33 p.m. |
| PD | Predicate disambiguation | batch_69fcd9017dd88190b32a73fe78909740 |
completed | May 7, 2026, 6:25 p.m. |
Created at: May 3, 2026, 4:32 p.m.