Triple
T8813234
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Melilotus |
E209714
|
entity |
| Predicate | fixesNitrogenWith |
P4281
|
FINISHED |
| Object | rhizobia bacteria |
—
|
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: rhizobia bacteria | Statement: [Melilotus, fixesNitrogenWith, rhizobia bacteria]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fixesNitrogenWith Context triple: [Melilotus, fixesNitrogenWith, rhizobia bacteria]
-
A.
fixesNitrogen
chosen
Indicates that the subject converts atmospheric nitrogen into biologically usable forms through nitrogen fixation.
-
B.
fixedBy
Indicates that one entity is repaired, corrected, or resolved through the action or intervention of another entity.
-
C.
nutrientUptake
Indicates the process by which an entity absorbs or takes in nutrients from its surrounding environment.
-
D.
typeOfFixing
Indicates the specific method or manner in which one entity is fastened, attached, or secured to another.
-
E.
ionizes
Indicates that one entity causes another entity to gain or lose electrons, thereby converting it into an ion.
- 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_69ca8363f3308190a47e3f1ebd51f613 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc5ff02e9c819080a8e45ba9ca044e |
completed | March 31, 2026, 11:59 p.m. |
| PD | Predicate disambiguation | batch_69cc5c1f28ec8190a34311cb412920c2 |
completed | March 31, 2026, 11:43 p.m. |
Created at: March 30, 2026, 6:45 p.m.