Triple
T16883080
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hyoscyamus |
E421469
|
entity |
| Predicate | isDangerousAtDose |
P54183
|
FINISHED |
| Object | relatively low doses |
—
|
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: relatively low doses | Statement: [Hyoscyamus, isDangerousAtDose, relatively low doses]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isDangerousAtDose Context triple: [Hyoscyamus, isDangerousAtDose, relatively low doses]
-
A.
dangerousWhen
Indicates that one entity becomes harmful, risky, or unsafe under the conditions or in the presence of another entity or situation.
-
B.
riskOfOverdose
Indicates a likelihood or potential that the subject will experience a drug or substance overdose, given certain conditions or factors.
-
C.
notableToxicity
chosen
Indicates that an entity is recognized for having a significant level or history of toxicity, harm, or detrimental effects in its context or interactions.
-
D.
toxicTo
Indicates that one entity causes harm, poisoning, or adverse effects to another when exposed or applied.
-
E.
LD50DermalHumanEstimate
Indicates the estimated dermal (skin exposure) dose of a substance that is lethal to 50% of a human population under specified conditions.
- 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_69d889d470fc8190b4aec199636c0c56 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e3bbbdffd8819093f1efd91f6d49dc |
completed | April 18, 2026, 5:13 p.m. |
| PD | Predicate disambiguation | batch_69e32b90ec3c819099c51bb7baf2984c |
completed | April 18, 2026, 6:58 a.m. |
Created at: April 10, 2026, 5:29 a.m.