Triple
T29178961
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Leptospira interrogans |
E739694
|
entity |
| Predicate | reservoirHosts |
P113521
|
FINISHED |
| Object | rodents |
—
|
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: rodents | Statement: [Leptospira interrogans, reservoirHosts, rodents]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reservoirHosts Context triple: [Leptospira interrogans, reservoirHosts, rodents]
-
A.
reservoirHost
chosen
Indicates that one entity serves as a natural long-term host in which a pathogen is maintained and from which it can be transmitted to other susceptible entities.
-
B.
reservoirAlsoKnownAs
Indicates that a reservoir is referred to by an alternative name or alias.
-
C.
relatedReservoir
Indicates that one reservoir has a specified relationship or association with another reservoir, such as physical connection, shared resources, or functional linkage.
-
D.
reservoir
Indicates that one entity serves as a storage or containment source (often for a resource) that can supply or affect another entity.
-
E.
usesReservoir
Indicates that one entity draws upon, depends on, or operates using a particular reservoir as a resource or source.
- 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_69f07cb74c2c8190ad396487fcb4fde6 |
completed | April 28, 2026, 9:24 a.m. |
| NER | Named-entity recognition | batch_69f66343216c81909f1a6503d1538608 |
completed | May 2, 2026, 8:49 p.m. |
| PD | Predicate disambiguation | batch_69f65c24f8b48190af81b575f3c15be5 |
completed | May 2, 2026, 8:18 p.m. |
Created at: April 28, 2026, 11:56 a.m.