Triple
T36186756
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | picrotoxin |
E1046866
|
entity |
| Predicate | hasToxicEffect |
P54346
|
FINISHED |
| Object | respiratory failure at high 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: respiratory failure at high doses | Statement: [picrotoxin, hasToxicEffect, respiratory failure at high doses]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasToxicEffect Context triple: [picrotoxin, hasToxicEffect, respiratory failure at high doses]
-
A.
toxinEffect
chosen
Indicates the harmful impact or physiological response caused by a toxin on a target entity.
-
B.
toxicTo
Indicates that one entity causes harm, poisoning, or adverse effects to another when exposed or applied.
-
C.
hasToxicSap
Indicates that an entity produces or contains sap that is harmful or poisonous to other organisms.
-
D.
poisonUsed
Indicates that one entity employed poison as a means to harm, kill, or incapacitate another entity.
-
E.
toxicityRoute
Indicates the route or pathway through which a toxic effect or substance is delivered or exposed to an entity.
- 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_69f76e3d4fbc81908c159c7beeb4ce00 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fd509e6bc08190b263923c2f40fea3 |
completed | May 8, 2026, 2:55 a.m. |
| PD | Predicate disambiguation | batch_69fd4fd1a58881909d4b84de1b24e380 |
completed | May 8, 2026, 2:52 a.m. |
Created at: May 3, 2026, 4:08 p.m.