Triple
T9477919
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | CD4+ T cells |
E228561
|
entity |
| Predicate | lacksMarker |
P1817
|
FINISHED |
| Object | CD8 |
—
|
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: CD8 | Statement: [CD4+ T cells, lacksMarker, CD8]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lacksMarker Context triple: [CD4+ T cells, lacksMarker, CD8]
-
A.
hasMarker
Indicates that one entity possesses, is associated with, or is identified by a specific marker.
-
B.
doesNotHave
chosen
Indicates that one entity lacks, is missing, or is not in possession of another entity or attribute.
-
C.
lacksNotabilityAs
Indicates that one entity is considered insufficiently notable or significant to be associated with or classified as the other entity.
-
D.
marque
Indicates that one entity is the brand or make associated with another entity, such as a product, vehicle, or manufactured item.
-
E.
usedMark
Indicates that one entity has employed or applied a particular mark, symbol, or indicator in some context or action.
- 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_69ca847162c48190b079076c9595513c |
completed | March 30, 2026, 2:10 p.m. |
| NER | Named-entity recognition | batch_69cd801386948190890133f622ff360b |
completed | April 1, 2026, 8:29 p.m. |
| PD | Predicate disambiguation | batch_69cca55f01b081908dc0f12eaa45f832 |
completed | April 1, 2026, 4:55 a.m. |
Created at: March 30, 2026, 7:54 p.m.