Triple
T25336856
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roquefort-sur-Soulzon caves |
E635299
|
entity |
| Predicate | supportsMicroorganism |
P122182
|
FINISHED |
| Object | native cave microflora |
—
|
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: native cave microflora | Statement: [Roquefort-sur-Soulzon caves, supportsMicroorganism, native cave microflora]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsMicroorganism Context triple: [Roquefort-sur-Soulzon caves, supportsMicroorganism, native cave microflora]
-
A.
isMicroorganism
Indicates that an entity is a microscopic living organism, such as a bacterium, virus, fungus, or protozoan.
-
B.
targetOrganism
Indicates that an action, process, or effect is directed toward or intended to impact a particular organism.
-
C.
hasOrganism
Indicates that one entity is an organism associated with, contained in, or otherwise possessed by another entity.
-
D.
includesOrganisms
chosen
Indicates that one entity contains, encompasses, or has as members one or more specified organisms.
-
E.
detectsOrganism
Indicates that one entity identifies, discovers, or observes the presence of another organism.
- 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_69e75a99bd6481909476115b35b9a8e4 |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f69edbb7648190bd89c57e0932eac1 |
completed | May 3, 2026, 1:03 a.m. |
| PD | Predicate disambiguation | batch_69f69d17e8d48190b30bcc2f4bd81eb2 |
completed | May 3, 2026, 12:55 a.m. |
Created at: April 21, 2026, 1:32 p.m.