Triple
T22871189
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | thioridazine |
E567199
|
entity |
| Predicate | hasChEMBLID |
P150058
|
FINISHED |
| Object | CHEMBL841 |
—
|
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: CHEMBL841 | Statement: [thioridazine, hasChEMBLID, CHEMBL841]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasChEMBLID Context triple: [thioridazine, hasChEMBLID, CHEMBL841]
-
A.
hasPubChemCID
Indicates that an entity (typically a chemical substance) is associated with a specific PubChem Compound Identifier (CID) in the PubChem database.
-
B.
hasDrugBankID
Indicates that an entity is associated with a specific identifier from the DrugBank database.
-
C.
hasMolecularTarget
Indicates that one entity (such as a drug or compound) is directed toward, binds to, or specifically interacts with a particular molecular target (such as a protein, receptor, or gene).
-
D.
hasHGNCID
Indicates that an entity (typically a gene) is associated with a specific identifier assigned by the HUGO Gene Nomenclature Committee (HGNC).
-
E.
CASNumber
Indicates that a chemical substance is identified by a specific unique CAS (Chemical Abstracts Service) registry number.
- F. None of above. chosen
Provenance (4 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_69e24589d8348190b96422d13a678bc1 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17f04b06481909004818ec8fc5a26 |
completed | April 29, 2026, 3:46 a.m. |
| PD | Predicate disambiguation | batch_69eed2d8c0608190afef4c4e530c0e2c |
completed | April 27, 2026, 3:07 a.m. |
| PDg | Predicate description generation | batch_69eeeb577e2081909f4a4e9c296535c0 |
completed | April 27, 2026, 4:51 a.m. |
Created at: April 17, 2026, 3:38 p.m.