Triple
T36599908
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Peyer’s patches |
E902888
|
entity |
| Predicate | antigenUptakeMediatedBy |
P185921
|
FINISHED |
| Object | M cells |
—
|
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: M cells | Statement: [Peyer’s patches, antigenUptakeMediatedBy, M cells]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: antigenUptakeMediatedBy Context triple: [Peyer’s patches, antigenUptakeMediatedBy, M cells]
-
A.
antigen
Indicates that one entity functions as an antigen in relation to another, typically provoking or being recognized by an immune response.
-
B.
antigensExpressedOn
Indicates that specific antigens are present on the surface of a given cell or biological structure.
-
C.
antigenLocation
Indicates the location or site within an organism or environment where a specific antigen is present or found.
-
D.
associatedWithAntibody
Indicates a relationship where something is linked or connected to a specific antibody, such as being produced by it, targeted by it, or otherwise functionally related to it.
-
E.
immuneResponseType
Indicates the specific kind or category of immune reaction that occurs in response to a particular stimulus or agent.
- F. None of above. chosen
Provenance (4 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_69f76e66b7b88190848f7a3e1188915f |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7c371931c8190afb1d4dd5157f92c |
completed | May 3, 2026, 9:51 p.m. |
| PD | Predicate disambiguation | batch_69f7c1baf25c8190a78dd54a400d2c50 |
completed | May 3, 2026, 9:44 p.m. |
| PDg | Predicate description generation | batch_69f7c3705b5c81908c84004543a71c07 |
completed | May 3, 2026, 9:51 p.m. |
Created at: May 3, 2026, 4:11 p.m.