Triple
T20079219
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Will Hurley |
E499952
|
entity |
| Predicate | coFounded |
P104
|
FINISHED |
| Object | Strangeworks |
—
|
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: Strangeworks | Statement: [Will Hurley, coFounded, Strangeworks]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Strangeworks Context triple: [Will Hurley, coFounded, Strangeworks]
-
A.
Strangeworks
chosen
Strangeworks is a technology company focused on making quantum computing and related advanced computing technologies more accessible to developers and enterprises.
-
B.
Anyscale
Anyscale is a company that builds tools and infrastructure to simplify and scale distributed computing and AI applications in the cloud.
-
C.
Orion Platform
Orion Platform is SolarWinds’ flagship IT infrastructure monitoring and management suite used to oversee networks, servers, applications, and other critical systems from a unified console.
-
D.
Autonomica AB
Autonomica AB is a Swedish company known for operating critical internet infrastructure services, including DNS and root server operations.
-
E.
Palantir Foundry
Palantir Foundry is a data integration and analytics platform that enables organizations to unify, model, and operationalize their data for decision-making and complex workflows.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69da627770948190997f486f9a2e370f |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e6643e216c819088c002fc1de2772a |
completed | April 20, 2026, 5:37 p.m. |
Created at: April 11, 2026, 3:40 p.m.