Triple
T28818204
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Epstein–Barr virus infection |
E727688
|
entity |
| Predicate | serologicMarker |
P22710
|
FINISHED |
| Object | heterophile antibodies |
—
|
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: heterophile antibodies | Statement: [Epstein–Barr virus infection, serologicMarker, heterophile antibodies]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: serologicMarker Context triple: [Epstein–Barr virus infection, serologicMarker, heterophile antibodies]
-
A.
usedAsBiomarkerFor
Indicates that one entity serves as a biomarker for another entity, typically signaling the presence, progression, or risk of a specific condition or biological state.
-
B.
diagnosticBiomarker
chosen
Indicates that one entity serves as a measurable biological indicator used to detect, confirm, or help diagnose a condition or disease in another entity.
-
C.
antigen
Indicates that one entity functions as an antigen in relation to another, typically provoking or being recognized by an immune response.
-
D.
clinicalSignOf
Indicates that one clinical sign is evidence or manifestation of a particular disease, condition, or underlying medical state.
-
E.
indicationTestedIn
Indicates that a particular medical indication (disease or condition) has been evaluated or tested in a specified clinical study or experimental context.
- 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_69f0319d09088190bbf14cdf1987792a |
completed | April 28, 2026, 4:03 a.m. |
| NER | Named-entity recognition | batch_69f658f54d4c819098307e82a2a6e892 |
completed | May 2, 2026, 8:05 p.m. |
| PD | Predicate disambiguation | batch_69f65762b5e481908a30ca963dcba4be |
completed | May 2, 2026, 7:58 p.m. |
Created at: April 28, 2026, 6:33 a.m.