Triple
T36599420
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | neratinib |
E902878
|
entity |
| Predicate | bindsCovalentlyTo |
P37017
|
FINISHED |
| Object | HER2 kinase domain |
—
|
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 kinase domain | Statement: [neratinib, bindsCovalentlyTo, HER2 kinase domain]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bindsCovalentlyTo Context triple: [neratinib, bindsCovalentlyTo, HER2 kinase domain]
-
A.
bindsNucleotide
Indicates that one entity physically attaches to or associates with a nucleotide molecule.
-
B.
bindsDNAAs
Indicates that one entity physically attaches to DNA, forming a specific binding interaction with it.
-
C.
hasProteinBinding
Indicates that one entity is capable of physically binding to or interacting specifically with a protein.
-
D.
bindingInteraction
Indicates a specific binding relationship where one entity physically or functionally attaches to, or forms a stable association with, another entity.
-
E.
bindsTo
chosen
Indicates that one entity physically or functionally attaches or connects to another, often with some specificity or selectivity in the interaction.
- 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_69f76e66b7b88190848f7a3e1188915f |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7c371931c8190afb1d4dd5157f92c |
completed | May 3, 2026, 9:51 p.m. |
| PD | Predicate disambiguation | batch_69f7c1baf25c8190a78dd54a400d2c50 |
completed | May 3, 2026, 9:44 p.m. |
Created at: May 3, 2026, 4:11 p.m.