Triple
T3804156
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yosemite |
E91761
|
entity |
| Predicate | targetCompanies |
P51850
|
FINISHED |
| Object | biotech startups |
—
|
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: biotech startups | Statement: [Yosemite, targetCompanies, biotech startups]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: targetCompanies Context triple: [Yosemite, targetCompanies, biotech startups]
-
A.
typicalEmployer
Indicates that one entity is the kind of organization or person that commonly or usually employs the other entity.
-
B.
selectedCompany
Indicates that a particular company has been chosen or designated from a set of possible companies.
-
C.
targetOrganization
Indicates that one entity is the organization that is the focus, recipient, or primary subject of another entity’s action, service, or relationship.
-
D.
portfolioCompany
Indicates that one entity is a company in which another entity (typically an investor or investment fund) holds an ownership stake as part of its investment portfolio.
-
E.
typicalEmployerUnit
Indicates that one entity is the standard or characteristic organizational unit that employs or is expected to employ another entity.
- 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_69aed96354f48190a768966d6bd19b04 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aee8db8a288190afd1e3b9dcf02e97 |
completed | March 9, 2026, 3:35 p.m. |
| PD | Predicate disambiguation | batch_69aee7461abc8190945716f4b93e1a18 |
completed | March 9, 2026, 3:29 p.m. |
| PDg | Predicate description generation | batch_69aee8d9b328819080158be59e5bcc97 |
completed | March 9, 2026, 3:35 p.m. |
Created at: March 9, 2026, 3:15 p.m.