Triple
T11074460
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | B lymphocytes |
E261828
|
entity |
| Predicate | express |
P88336
|
FINISHED |
| Object | CD20 |
E261827
|
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: CD20 | Statement: [B lymphocytes, express, CD20]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: CD20 Context triple: [B lymphocytes, express, CD20]
-
A.
CD20 protein
chosen
CD20 protein is a cell-surface antigen found primarily on B lymphocytes and is a key therapeutic target in certain autoimmune diseases and B-cell malignancies.
-
B.
CD21
CD21 is a complement receptor (CR2) found on B cells and follicular dendritic cells that plays a key role in B cell activation and the immune response.
-
C.
CD22
CD22 is a B-cell–specific surface glycoprotein that functions as an inhibitory co-receptor modulating B cell receptor signaling and immune responses.
-
D.
CD38
CD38 is a cell surface glycoprotein with ectoenzyme and receptor functions, highly expressed on plasma cells and targeted in therapies for multiple myeloma and other hematologic malignancies.
-
E.
CD32
CD32 is a low-affinity Fc gamma receptor (FcγRII) found on various immune cells that plays a key role in modulating antibody-dependent immune responses.
- 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_69d6aa9983c08190b0ef61603b69feac |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d7994e32fc8190a6591d9e82b68f75 |
completed | April 9, 2026, 12:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e3e76a49fc8190945f4770bf808b43 |
completed | April 18, 2026, 8:19 p.m. |
Created at: April 8, 2026, 9:26 p.m.