Triple
T36618909
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ERBB4 |
E903678
|
entity |
| Predicate | hasAlternativeSplicing |
P170165
|
FINISHED |
| Object | multiple isoforms |
—
|
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: multiple isoforms | Statement: [ERBB4, hasAlternativeSplicing, multiple isoforms]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAlternativeSplicing Context triple: [ERBB4, hasAlternativeSplicing, multiple isoforms]
-
A.
alternativeSplicingFeature
Indicates that a genomic region or element participates in an alternative splicing event, distinguishing it as a feature involved in generating splice variants.
-
B.
hasIsoform
chosen
Indicates that one biological variant or form of a molecule, typically a protein or gene product, is an alternative isoform of another.
-
C.
hasShortIntrons
Indicates that the entity possesses introns whose lengths are relatively short compared to a defined standard or typical intron size.
-
D.
hasAlternativeAnalyses
Indicates that an entity is associated with one or more different or optional analyses that can be considered as alternatives to a primary analysis.
-
E.
hasAlternativeHypothesisLocation
Indicates that there is another possible location proposed as an alternative to the primary hypothesized location.
- 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_69f76e6960e4819092047756ceb9a17e |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fe1fd637c08190aa95cd2478c278cb |
completed | May 8, 2026, 5:39 p.m. |
| PD | Predicate disambiguation | batch_69fe19344bb481909b5e2144155e4add |
completed | May 8, 2026, 5:11 p.m. |
Created at: May 3, 2026, 4:11 p.m.