Triple
T19245319
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | INS gene |
E481234
|
entity |
| Predicate | encodes |
P14248
|
FINISHED |
| Object | preproinsulin |
—
|
NE NERFINISHED |
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: [INS gene, encodes, preproinsulin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: preproinsulin Context triple: [INS gene, encodes, preproinsulin]
-
A.
insulin
chosen
Insulin is a peptide hormone produced by the pancreas that regulates blood glucose levels and is essential in the treatment of diabetes.
-
B.
Insulindia
Insulindia is a historical and geographical term referring to the Malay Archipelago, the vast group of islands in Southeast Asia between the Asian mainland and Australia.
-
C.
HGH
HGH is the IATA airport code for Hangzhou Xiaoshan International Airport, the main international airport serving Hangzhou in eastern China.
-
D.
Hépar
Hépar is a French natural mineral water brand known for its high magnesium content and digestive health benefits.
-
E.
Genotropin
Genotropin is a synthetic human growth hormone medication used to treat growth failure in children and adults with growth hormone deficiency and certain other conditions.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e8cd9d1081908a181d02b88b59b8 |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e5fb2c34e88190a338e5a7ba906425 |
completed | April 20, 2026, 10:08 a.m. |
Created at: April 10, 2026, 1:27 p.m.