Triple
T11074440
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | CD20 protein |
E261827
|
entity |
| Predicate | alternativeName |
P39
|
FINISHED |
| Object | LEU‑16 antigen |
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: LEU‑16 antigen | Statement: [CD20 protein, alternativeName, LEU‑16 antigen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: LEU‑16 antigen Context triple: [CD20 protein, alternativeName, LEU‑16 antigen]
-
A.
CD46
CD46 is a human cell-surface complement regulatory protein that also serves as an entry receptor for various pathogens, including certain adenoviruses and measles virus.
-
B.
HLA
HLA is the three-letter IATA airport code for Lanseria International Airport, a major privately owned airport serving the Johannesburg region in South Africa.
-
C.
CD3 complex
The CD3 complex is a multi-subunit protein complex associated with the T-cell receptor that is essential for T-cell activation and signal transduction in the immune system.
-
D.
IL-64
IL-64 is a major east–west state highway in Illinois that runs from the Mississippi River through the Chicago metropolitan area.
-
E.
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.
- 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_69e3c8cc77988190aad54f56dbd0f8cf |
completed | April 18, 2026, 6:09 p.m. |
Created at: April 8, 2026, 9:26 p.m.