Triple
T768541
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Silver |
E16227
|
entity |
| Predicate | CASNumber |
P19728
|
FINISHED |
| Object | 7440-22-4 |
—
|
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: 7440-22-4 | Statement: [Silver, CASNumber, 7440-22-4]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: CASNumber Context triple: [Silver, CASNumber, 7440-22-4]
-
A.
hasAtomicNumber
Indicates that one entity is the chemical element whose atomic number (number of protons in its nucleus) is given by the other entity.
-
B.
citationNumber
Indicates the specific numeric identifier assigned to a citation within a document or reference list.
-
C.
hasProtonNumber
Indicates that an entity (typically a chemical element or atom) possesses a specific number of protons in its nucleus.
-
D.
hasMassNumber
Indicates that an atomic nucleus or isotope is associated with a specific mass number, representing the total count of protons and neutrons it contains.
-
E.
opusNumber
Indicates that a creative work is assigned a specific opus number identifying its place within a creator’s catalog or chronological sequence of works.
- 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_69a49369a0848190af883934cee3db4c |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a765ba688190ab328bb159583077 |
completed | March 1, 2026, 8:53 p.m. |
| PD | Predicate disambiguation | batch_69a4a5074c788190a74fc20ad24e2d26 |
completed | March 1, 2026, 8:43 p.m. |
| PDg | Predicate description generation | batch_69a4a7648a6c8190a9051a3d177ff7e2 |
completed | March 1, 2026, 8:53 p.m. |
Created at: March 1, 2026, 7:37 p.m.