Triple
T4945903
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | insulin |
E111048
|
entity |
| Predicate | synthesizedAs |
P60097
|
FINISHED |
| Object | preproinsulin |
—
|
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: preproinsulin | Statement: [insulin, synthesizedAs, preproinsulin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: synthesizedAs Context triple: [insulin, synthesizedAs, preproinsulin]
-
A.
synthesisType
Indicates the specific method, process, or pathway by which something is synthesized or produced.
-
B.
constructedAs
Indicates that one entity is built, formed, or created in the manner, structure, or configuration specified by another entity.
-
C.
allowsSynthesisFromSources
Indicates that one entity permits the creation or production of something using specified source entities or materials.
-
D.
consolidatedAs
Indicates that one entity has been combined, merged, or unified into another entity to form a single consolidated whole.
-
E.
firstSynthesisTarget
Indicates that an entity is the initial or primary target selected for synthesis in a process or workflow.
- 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_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. |
| PDg | Predicate description generation | batch_69bd6fa2d2088190ae444d3d0e47d5d2 |
completed | March 20, 2026, 4:02 p.m. |
Created at: March 20, 2026, 1:31 p.m.