Triple
T1808958
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chemical Abstracts Service |
E40284
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | CAS Registry database |
E205108
|
NE 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: CAS Registry database | Statement: [Chemical Abstracts Service, hasPart, CAS Registry database]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: CAS Registry database Context triple: [Chemical Abstracts Service, hasPart, CAS Registry database]
-
A.
CAS Registry Numbers
chosen
CAS Registry Numbers are unique numerical identifiers assigned to chemical substances, widely used to unambiguously reference specific chemicals in scientific, regulatory, and industrial contexts.
-
B.
Chemical Abstracts Service
Chemical Abstracts Service is a division of the American Chemical Society that provides a comprehensive database of chemical literature and substances, widely used for research and indexing in the chemical sciences.
-
C.
CAS References database
The CAS References database is a comprehensive bibliographic resource curated by the Chemical Abstracts Service that indexes scientific literature and patent references related to chemistry and related disciplines.
-
D.
SciFinder-n
SciFinder-n is a comprehensive research discovery platform from Chemical Abstracts Service that enables scientists to search and analyze chemical substances, reactions, literature, and related scientific data.
-
E.
TSCA Inventory of chemical substances
The TSCA Inventory of chemical substances is the official U.S. Environmental Protection Agency list of chemical substances that are manufactured, processed, or imported in the United States for commercial purposes.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69a88643a3388190a612f2ebe1fb29e7 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69aa65c310d88190bfd9c27fa238e648 |
completed | March 6, 2026, 5:27 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69add1bd5f68819080a4fe06e3e1f76d |
completed | March 8, 2026, 7:45 p.m. |
Created at: March 4, 2026, 7:32 p.m.