Triple
T22717304
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | fluconazole |
E561768
|
entity |
| Predicate | notActiveAgainst |
P84339
|
FINISHED |
| Object | most Aspergillus species |
—
|
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: most Aspergillus species | Statement: [fluconazole, notActiveAgainst, most Aspergillus species]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notActiveAgainst Context triple: [fluconazole, notActiveAgainst, most Aspergillus species]
-
A.
usedAgainst
Indicates that one entity is employed, applied, or deployed in opposition to, or for the purpose of affecting, another entity.
-
B.
effectivenessAgainst
chosen
Indicates how well one entity performs in countering, influencing, or mitigating the impact of another entity.
-
C.
notReactiveWith
Indicates that one entity does not undergo a chemical or functional reaction when brought into contact or association with another entity.
-
D.
nonCombatEquivalentOf
Indicates that one entity serves as the non-combat or peaceful counterpart of another entity that is oriented toward combat or warfare.
-
E.
notAvailableFor
Indicates that an entity is currently not accessible, usable, or eligible for a particular action, purpose, or association.
- 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_69e2454fc984819088213b58ee87a002 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1790ecbc48190926d16b20b674dbd |
completed | April 29, 2026, 3:20 a.m. |
| PD | Predicate disambiguation | batch_69ee62bd657c81909f7b01245b080a5f |
completed | April 26, 2026, 7:08 p.m. |
Created at: April 17, 2026, 3:19 p.m.