Triple
T9833879
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | diphtheria antitoxin |
E239052
|
entity |
| Predicate | sourceOrganism |
P18418
|
FINISHED |
| Object | equine |
—
|
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: equine | Statement: [diphtheria antitoxin, sourceOrganism, equine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sourceOrganism Context triple: [diphtheria antitoxin, sourceOrganism, equine]
-
A.
targetOrganism
Indicates that an action, process, or effect is directed toward or intended to impact a particular organism.
-
B.
studiedOrganism
Indicates that an entity conducted study or research on a particular organism.
-
C.
originSpecies
chosen
Indicates that one entity is the original or source species from which another entity is derived, evolved, or produced.
-
D.
organismType
Indicates the biological classification or kind of organism that an entity is.
-
E.
isModelOrganism
Indicates that one organism is used as a representative experimental system for studying biological processes relevant to other organisms.
- 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_69ca84e314108190978324a4bdb959f8 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdb3385054819094145c96204e3f0d |
completed | April 2, 2026, 12:07 a.m. |
| PD | Predicate disambiguation | batch_69cd03e30bc08190816c0a6d29c21b0f |
completed | April 1, 2026, 11:39 a.m. |
Created at: March 30, 2026, 8:32 p.m.