Triple
T9723271
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sarah Altman |
E235534
|
entity |
| Predicate | requiresMedication |
P69332
|
FINISHED |
| Object | insulin |
—
|
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: insulin | Statement: [Sarah Altman, requiresMedication, insulin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: requiresMedication Context triple: [Sarah Altman, requiresMedication, insulin]
-
A.
requiresPremedication
Indicates that one entity must receive premedication (a preparatory medical treatment) before another specified procedure, treatment, or action can occur.
-
B.
doseAdjustmentRequiredIn
Indicates that a change in the amount or frequency of a treatment or medication is necessary within a specified context, such as a condition, setting, or patient group.
-
C.
hasDrug
chosen
Indicates that an entity possesses, is treated with, or is associated with a particular drug.
-
D.
usesDrug
Indicates that an entity consumes, administers, or otherwise makes use of a specified drug.
-
E.
hasDosingRegimen
Indicates that an entity is associated with a specific dosing regimen, defining how and when a dose is to be administered.
- 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_69ca84d0123c819096f9dc3b6abb0881 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cd9e75abd48190a6e6679ec51496e8 |
completed | April 1, 2026, 10:38 p.m. |
| PD | Predicate disambiguation | batch_69cd03c6ffc88190a5e9569e19122ad5 |
completed | April 1, 2026, 11:38 a.m. |
Created at: March 30, 2026, 8:20 p.m.