Triple
T2371108
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Perjeta |
E46091
|
entity |
| Predicate | inhibits |
P37861
|
FINISHED |
| Object | HER2 dimerization |
—
|
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 dimerization | Statement: [Perjeta, inhibits, HER2 dimerization]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inhibits Context triple: [Perjeta, inhibits, HER2 dimerization]
-
A.
discourages
Indicates an action or influence that deters, dissuades, or reduces the likelihood of someone performing a particular behavior or pursuing a certain outcome.
-
B.
prohibits
Indicates that one entity forbids or disallows another entity from performing a specific action or being in a certain state.
-
C.
negates
Indicates that one entity denies, contradicts, or renders false the assertion, state, or effect expressed by another.
-
D.
imposes
Indicates that one entity enforces, applies, or places a rule, condition, burden, or obligation upon another entity.
-
E.
in
Indicates that one entity is located within the spatial, temporal, or conceptual bounds of another entity.
- F. None of above. chosen
Provenance (4 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_69a88a145268819083e2736cb835c696 |
completed | March 4, 2026, 7:37 p.m. |
| NER | Named-entity recognition | batch_69abc771302481908540e31abb5aeeba |
completed | March 7, 2026, 6:36 a.m. |
| PD | Predicate disambiguation | batch_69abc59b88348190a2d6c08f69974117 |
completed | March 7, 2026, 6:28 a.m. |
| PDg | Predicate description generation | batch_69abc6443c6c8190b932de2abd8eb28f |
completed | March 7, 2026, 6:31 a.m. |
Created at: March 4, 2026, 7:56 p.m.