Triple
T19992597
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | APOE gene |
E494100
|
entity |
| Predicate | UniProtProteinEncoded |
P90100
|
FINISHED |
| Object | P02649 |
—
|
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: P02649 | Statement: [APOE gene, UniProtProteinEncoded, P02649]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: UniProtProteinEncoded Context triple: [APOE gene, UniProtProteinEncoded, P02649]
-
A.
uniprotId
chosen
Indicates that an entity is associated with a specific UniProt database identifier for a protein.
-
B.
proteinProduct
Indicates that one entity is the protein that is produced or encoded by another entity (such as a gene or transcript).
-
C.
encodedByGene
Indicates that a particular gene is responsible for producing or specifying the sequence of a given molecule (such as a protein or RNA).
-
D.
proteinContent
Indicates the amount or proportion of protein present in a given entity or substance.
-
E.
NCBIGeneID
Indicates a relationship that assigns or links an entity to its unique gene identifier as defined in the NCBI Gene database.
- 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_69da626a67648190af9653832a3aeced |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e65fe10ffc81908c94168b0a8ea9c9 |
completed | April 20, 2026, 5:18 p.m. |
| PD | Predicate disambiguation | batch_69e537fd311881908448f2aea8b4812e |
completed | April 19, 2026, 8:15 p.m. |
Created at: April 11, 2026, 3:31 p.m.