Triple
T9791062
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | BSX |
E237607
|
entity |
| Predicate | hasUnderlyingCompanyBusinessFocus |
P6749
|
FINISHED |
| Object | interventional medical devices |
—
|
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: interventional medical devices | Statement: [BSX, hasUnderlyingCompanyBusinessFocus, interventional medical devices]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasUnderlyingCompanyBusinessFocus Context triple: [BSX, hasUnderlyingCompanyBusinessFocus, interventional medical devices]
-
A.
underlyingCompanyBusinessFocus
chosen
Indicates the primary industry, sector, or type of business activity that the underlying company is focused on.
-
B.
hasUnderlyingCompanyBusinessModel
Indicates that one entity possesses or is based on a specific company business model that underlies its structure, operations, or value creation.
-
C.
hasUnderlyingCompanyOperationsIn
Indicates that a company’s core or foundational business activities take place within a specified geographic location or jurisdiction.
-
D.
hasUnderlyingCompanyWellKnownFor
Indicates that an entity is associated with an underlying company that is widely recognized or notable.
-
E.
industryOfUnderlyingCompany
Indicates the industry sector in which the underlying company associated with this entity operates.
- 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_69ca84dc04488190b9c91193976c0960 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cda215b3108190a897552e1dc91cc4 |
completed | April 1, 2026, 10:54 p.m. |
| PD | Predicate disambiguation | batch_69cd03d77c6c81909b675955bf113320 |
completed | April 1, 2026, 11:39 a.m. |
Created at: March 30, 2026, 8:28 p.m.