Triple
T985392
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chinese Rocks |
E21265
|
entity |
| Predicate | associatedDrug |
P7501
|
FINISHED |
| Object | heroin |
—
|
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: heroin | Statement: [Chinese Rocks, associatedDrug, heroin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedDrug Context triple: [Chinese Rocks, associatedDrug, heroin]
-
A.
hasNotableDrug
chosen
Indicates that an entity is associated with a drug that is considered notable or significant in some recognized context.
-
B.
notablyAssociatedWith
Indicates that one entity is prominently or distinctively connected with another in a way that is especially noteworthy or remarkable.
-
C.
mayBeComorbidWith
Indicates that two conditions or disorders can occur together in the same individual, potentially influencing each other’s presence or severity.
-
D.
hasTargetDisease
Indicates that an entity (such as a treatment, study, or intervention) is directed toward, intended to affect, or primarily concerned with a specified disease.
-
E.
treats
Indicates that one entity provides medical care or therapeutic intervention to another 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_69a493c383dc8190a03257f22d4b4183 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b4959fe48190a78bd811cbc888ab |
completed | March 1, 2026, 9:50 p.m. |
| PD | Predicate disambiguation | batch_69a4b2abccbc8190a83af432f89eacf5 |
completed | March 1, 2026, 9:42 p.m. |
Created at: March 1, 2026, 7:41 p.m.