Triple
T2370990
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Herceptin |
E46088
|
entity |
| Predicate | requiresTestingFor |
P17595
|
FINISHED |
| Object | HER2 overexpression |
—
|
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 overexpression | Statement: [Herceptin, requiresTestingFor, HER2 overexpression]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: requiresTestingFor Context triple: [Herceptin, requiresTestingFor, HER2 overexpression]
-
A.
requiresComplianceTestingBy
Indicates that one entity must undergo compliance testing conducted or overseen by another entity.
-
B.
requiresDetectionOf
Indicates that one entity can only occur, be valid, or proceed if another entity has first been detected or identified.
-
C.
isUsedToTest
Indicates that one entity serves as a means or tool for evaluating, examining, or verifying another entity.
-
D.
requiresFinding
chosen
Indicates that one entity’s validity, execution, or completion is contingent upon a specific finding or determination being made about another entity.
-
E.
requiresSoftware
Indicates that one entity depends on specific software being present or installed in order to function, operate, or be used.
- 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_69a88a145268819083e2736cb835c696 |
completed | March 4, 2026, 7:37 p.m. |
| NER | Named-entity recognition | batch_69abc76f5aec8190867d621e6849258c |
completed | March 7, 2026, 6:36 a.m. |
| PD | Predicate disambiguation | batch_69abc59b88348190a2d6c08f69974117 |
completed | March 7, 2026, 6:28 a.m. |
Created at: March 4, 2026, 7:56 p.m.