Triple
T8357230
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Guillain–Barré syndrome |
E196711
|
entity |
| Predicate | hasPrimarySymptom |
P2896
|
FINISHED |
| Object | ascending muscle weakness |
—
|
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: ascending muscle weakness | Statement: [Guillain–Barré syndrome, hasPrimarySymptom, ascending muscle weakness]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPrimarySymptom Context triple: [Guillain–Barré syndrome, hasPrimarySymptom, ascending muscle weakness]
-
A.
hasPossibleSymptom
Indicates that an entity (such as a condition or disease) may be associated with a particular symptom that can potentially occur.
-
B.
symptom
chosen
Indicates that a particular condition, disease, or problem manifests through a specific observable sign or complaint.
-
C.
primaryDisease
Indicates that a disease is the main or principal medical condition affecting an entity, as opposed to secondary or comorbid conditions.
-
D.
hasHealthConcern
Indicates that an entity has a specific health-related issue, condition, or concern associated with it.
-
E.
symptomAssociatedWithInfection
Indicates that a particular symptom is linked to, or commonly occurs as a result of, a specific infection.
- 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_69ca82f08b348190bfb7881944bbff6f |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb804b57f88190907a4e4e389caf5f |
completed | March 31, 2026, 8:05 a.m. |
| PD | Predicate disambiguation | batch_69cb70ca25548190b0f90c5384e3fb3c |
completed | March 31, 2026, 6:59 a.m. |
Created at: March 30, 2026, 5:59 p.m.