Triple
T714780
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Elaeagnaceae |
E14288
|
entity |
| Predicate | rootSymbiont |
P13438
|
FINISHED |
| Object | Frankia 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: Frankia bacteria | Statement: [Elaeagnaceae, rootSymbiont, Frankia bacteria]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rootSymbiont Context triple: [Elaeagnaceae, rootSymbiont, Frankia bacteria]
-
A.
symbiontType
chosen
Indicates the specific kind or category of symbiotic relationship that exists between associated organisms.
-
B.
rhizoidType
Indicates the specific kind or category of rhizoid structure associated with an organism or anatomical feature.
-
C.
biota
Indicates the presence or composition of living organisms (flora, fauna, or other life forms) associated with a given entity or environment.
-
D.
rootStructure
Indicates that one entity serves as the primary or foundational structural element upon which another entity is based or organized.
-
E.
colonyFoundation
Indicates the event or process by which a colony is established or founded in a particular place by a founding entity.
- 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_69a4934a36e081909e7abef98b898a4e |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a5738e04819082eac673b3b7c4c2 |
completed | March 1, 2026, 8:45 p.m. |
| PD | Predicate disambiguation | batch_69a4a4f38898819089d79bad4f4ff2d2 |
completed | March 1, 2026, 8:43 p.m. |
Created at: March 1, 2026, 7:36 p.m.