Triple
T22492421
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Amphotericin B |
E556051
|
entity |
| Predicate | isBroadSpectrumAgainst |
P99743
|
FINISHED |
| Object | fungi |
—
|
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: fungi | Statement: [Amphotericin B, isBroadSpectrumAgainst, fungi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isBroadSpectrumAgainst Context triple: [Amphotericin B, isBroadSpectrumAgainst, fungi]
-
A.
isBroad
Indicates that something has a large width or extensive scope relative to a reference or context.
-
B.
effectivenessAgainst
Indicates how well one entity performs in countering, influencing, or mitigating the impact of another entity.
-
C.
spectrumOfActivity
chosen
Indicates the range and variety of targets, conditions, or effects over which an action, agent, or process is effective or operative.
-
D.
isBroadBased
Indicates that something has a wide scope or foundation, encompassing many elements, aspects, or participants rather than being narrow or limited.
-
E.
isResistant
Indicates that an entity can withstand, oppose, or is not significantly affected by a specified force, influence, or agent.
- 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_69e11e5445bc8190b6a9481926db3355 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15cb01b3481908a9143503b75167f |
completed | April 29, 2026, 1:19 a.m. |
| PD | Predicate disambiguation | batch_69e898be31448190be5ae7f5656f0497 |
completed | April 22, 2026, 9:45 a.m. |
Created at: April 16, 2026, 8:49 p.m.