Triple
T23650220
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NVS |
E584147
|
entity |
| Predicate | underlyingShareType |
P66662
|
FINISHED |
| Object | Novartis AG registered shares |
—
|
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: Novartis AG registered shares | Statement: [NVS, underlyingShareType, Novartis AG registered shares]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: underlyingShareType Context triple: [NVS, underlyingShareType, Novartis AG registered shares]
-
A.
sharesType
Indicates that two or more entities have the same type or belong to the same category.
-
B.
underlyingConstituentsType
Indicates the type or category of fundamental components that make up or underlie a given entity or structure.
-
C.
underlyingCompanyType
chosen
Indicates the classification or category of company that forms the basis or source for another related entity or instrument.
-
D.
sharesTypeWith
Indicates that two entities belong to the same type or category.
-
E.
underlyingAsset
Indicates that one asset serves as the fundamental reference or basis for the value, performance, or contractual terms of another financial instrument or derivative.
- 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_69e248fefafc81909656921192f30e80 |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b2885b408190a43dfed93309a4d6 |
completed | April 29, 2026, 7:26 a.m. |
| PD | Predicate disambiguation | batch_69f118d7903c8190bb590a71771e93af |
completed | April 28, 2026, 8:30 p.m. |
Created at: April 17, 2026, 6:49 p.m.