Triple
T33388728
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Seagen |
E854988
|
entity |
| Predicate | TukysaIndication |
P113308
|
FINISHED |
| Object | HER2-positive breast cancer |
—
|
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 cancer | Statement: [Seagen, TukysaIndication, HER2-positive breast cancer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: TukysaIndication Context triple: [Seagen, TukysaIndication, HER2-positive breast cancer]
-
A.
indicatedFor
Indicates...that one entity (typically a treatment, procedure, or product) is recommended or appropriate for use in relation to another entity (such as a condition, symptom, or patient group).
-
B.
treatmentIndication
chosen
Indicates that a treatment is intended to address, alleviate, or prevent a particular condition, symptom, or medical indication.
-
C.
canIndicate
Indicates that one entity has the potential or capacity to serve as a sign, signal, or evidence of another entity or condition.
-
D.
ties
Indicates that one entity fastens, secures, or binds another entity (or two entities together), typically using a flexible connector such as a string, rope, or similar medium.
-
E.
usesIndicator
Indicates that one entity employs or relies on another entity as an indicator, signal, or metric for assessment, decision-making, or interpretation.
- 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_69f3496d54048190a1cb91fdd7caa6ea |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f6f38159d08190980ad639e08f00f4 |
completed | May 3, 2026, 7:04 a.m. |
| PD | Predicate disambiguation | batch_69f6e3d7bee48190b94e0beb48a1d7fa |
completed | May 3, 2026, 5:57 a.m. |
Created at: May 1, 2026, 1:35 a.m.