Triple
T26245295
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Narya Capital |
E656426
|
entity |
| Predicate | hasPortfolioCompanyRegionFocus |
P95787
|
FINISHED |
| Object | Midwestern United States |
—
|
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: Midwestern United States | Statement: [Narya Capital, hasPortfolioCompanyRegionFocus, Midwestern United States]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPortfolioCompanyRegionFocus Context triple: [Narya Capital, hasPortfolioCompanyRegionFocus, Midwestern United States]
-
A.
portfolioRegion
chosen
Indicates the geographic region or market area associated with a given portfolio.
-
B.
targetInvestorRegion
Indicates the geographic region or market area that an investor is focused on or intended to invest in.
-
C.
hasHeadquartersInRegion
Indicates that an organization’s main administrative or corporate headquarters is located within a specified geographic region.
-
D.
associatedOrganizationFocus
Indicates that an organization is linked to or concerned with a particular area of activity, topic, or domain as a primary focus.
-
E.
notableRegionOfBusiness
Indicates that a specified geographic region is a significant or primary area in which an entity conducts its business activities.
- 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_69ee5b4c59a881909d9ee4fd013fffd5 |
completed | April 26, 2026, 6:37 p.m. |
| NER | Named-entity recognition | batch_69f6cee45590819086e489bfccbe4ac3 |
completed | May 3, 2026, 4:28 a.m. |
| PD | Predicate disambiguation | batch_69f6cc1188708190b8f0f56e595e6057 |
completed | May 3, 2026, 4:16 a.m. |
Created at: April 26, 2026, 9:05 p.m.