Triple
T2138511
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roche |
E46707
|
entity |
| Predicate | product |
P490
|
FINISHED |
| Object | Avastin |
E46087
|
NE 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: Avastin | Statement: [Roche, product, Avastin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Avastin Context triple: [Roche, product, Avastin]
-
A.
Avastin
chosen
Avastin is a widely used cancer drug (bevacizumab) that inhibits angiogenesis by targeting vascular endothelial growth factor (VEGF).
-
B.
Alimta
Alimta is a chemotherapy drug (pemetrexed) primarily used to treat malignant pleural mesothelioma and non-small cell lung cancer.
-
C.
Lucentis
Lucentis is a prescription anti-VEGF biologic drug used to treat several serious eye diseases, including wet age-related macular degeneration and diabetic macular edema, by inhibiting abnormal blood vessel growth in the retina.
-
D.
Herceptin
Herceptin is a targeted monoclonal antibody drug used primarily to treat HER2-positive breast cancer by blocking the HER2 receptor on cancer cells.
-
E.
Tecentriq
Tecentriq is an immunotherapy cancer drug (atezolizumab) that targets the PD-L1 protein to help the immune system attack tumors in various cancers.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69a88a174ab48190a5db20c132e5dccf |
completed | March 4, 2026, 7:37 p.m. |
| NER | Named-entity recognition | batch_69abbe012aa481909ffa0a50e58efabb |
completed | March 7, 2026, 5:56 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae51b1290c8190a08850b428c99a6c |
completed | March 9, 2026, 4:50 a.m. |
Created at: March 4, 2026, 7:44 p.m.