Triple
T19992690
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | APOE ε3 allele |
E494101
|
entity |
| Predicate | hasReferenceProteinID |
P90100
|
FINISHED |
| Object | UniProt P02649 (E3 isoform) |
—
|
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: UniProt P02649 (E3 isoform) | Statement: [APOE ε3 allele, hasReferenceProteinID, UniProt P02649 (E3 isoform)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasReferenceProteinID Context triple: [APOE ε3 allele, hasReferenceProteinID, UniProt P02649 (E3 isoform)]
-
A.
hasProteinFeature
Indicates that a protein possesses a specific structural or functional feature, such as a domain, motif, or modification site.
-
B.
uniprotId
chosen
Indicates that an entity is associated with a specific UniProt database identifier for a protein.
-
C.
hasProtein
Indicates that one entity contains, includes, or is associated with a specific protein.
-
D.
hasProteinBinding
Indicates that one entity is capable of physically binding to or interacting specifically with a protein.
-
E.
hasReferenceID
Indicates that an entity is associated with a specific reference identifier used to uniquely track or distinguish it.
- 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.