Triple
T32226464
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zaltrap |
E823215
|
entity |
| Predicate | originatorCompany |
P37135
|
FINISHED |
| Object | Regeneron Pharmaceuticals |
—
|
NE NERFINISHED |
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: Regeneron Pharmaceuticals | Statement: [Zaltrap, originatorCompany, Regeneron Pharmaceuticals]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originatorCompany Context triple: [Zaltrap, originatorCompany, Regeneron Pharmaceuticals]
-
A.
originatingCompany
chosen
Indicates the company from which something (such as a product, document, transaction, or request) originally comes or is issued.
-
B.
foundingCompany
Indicates that one entity is the company that established or created another entity (such as an organization, project, or subsidiary).
-
C.
parentCompanyOfOrigin
Indicates that one company is the original parent or source company from which another company was created, derived, or spun off.
-
D.
associatedCompanyOrigin
Indicates that there is a relationship between an entity and the country, region, or place where its associated company originates or is founded.
-
E.
originalCompanyAbbreviation
Indicates that an abbreviation represents the shortened or initial-based form of an original company’s full name.
- 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_69f3490b4f948190b99e4f999f5be25f |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_6a017969ff908190a7a1a46b3f5ae362 |
completed | May 11, 2026, 6:38 a.m. |
| PD | Predicate disambiguation | batch_6a017609ff4c8190aba8a1864d39a608 |
completed | May 11, 2026, 6:24 a.m. |
Created at: May 1, 2026, 12:38 a.m.