Triple
T11074312
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ERBB2 |
E261825
|
entity |
| Predicate | overexpressedIn |
P92779
|
FINISHED |
| Object | HER2-positive breast tumors |
—
|
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: HER2-positive breast tumors | Statement: [ERBB2, overexpressedIn, HER2-positive breast tumors]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: overexpressedIn Context triple: [ERBB2, overexpressedIn, HER2-positive breast tumors]
-
A.
expressedInCellType
Indicates that something (such as a gene, protein, or molecule) is expressed or present in a specified cell type.
-
B.
tissueExpression
chosen
Indicates the association between a biological entity (such as a gene or protein) and the specific tissue(s) in which it is expressed.
-
C.
antigensExpressedOn
Indicates that specific antigens are present on the surface of a given cell or biological structure.
-
D.
expressedOn
Indicates that something (such as a feature, marker, or characteristic) is present or manifested on a particular entity or surface.
-
E.
targetsGene
Indicates that one entity is directed toward, acts upon, or is intended to affect a specific gene.
- 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_69d6aa9983c08190b0ef61603b69feac |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d7994e32fc8190a6591d9e82b68f75 |
completed | April 9, 2026, 12:19 p.m. |
| PD | Predicate disambiguation | batch_69d74415403c81909778bcd829e8832e |
completed | April 9, 2026, 6:15 a.m. |
Created at: April 8, 2026, 9:26 p.m.