Triple
T4945923
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | insulin |
E111048
|
entity |
| Predicate | firstUsedClinicallyIn |
P55558
|
FINISHED |
| Object | 1922 |
—
|
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: 1922 | Statement: [insulin, firstUsedClinicallyIn, 1922]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstUsedClinicallyIn Context triple: [insulin, firstUsedClinicallyIn, 1922]
-
A.
firstHistoricalUse
Indicates that the subject entity represents the earliest known or recorded instance of the object entity being used or occurring in history.
-
B.
firstUsedOn
Indicates the date, time, or context in which something was initially applied, activated, or put into use on a particular object or entity.
-
C.
firstTestedBy
Indicates that an item, concept, or process was initially tested or tried out by a particular agent or entity.
-
D.
historicalPeriodOfFirstUse
chosen
Indicates the historical time period during which something was first used or came into use.
-
E.
isFirstDrugApprovedFor
Indicates that a drug is the earliest or original medication approved for treating a particular condition, disease, or indication.
- 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_69bd441721cc819085c7e33fe0876818 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd70aa890c81908e685ec5e88cae1f |
completed | March 20, 2026, 4:07 p.m. |
| PD | Predicate disambiguation | batch_69bd6c3aa1388190b3e0c8ee1ba1e4fa |
completed | March 20, 2026, 3:48 p.m. |
Created at: March 20, 2026, 1:31 p.m.