Triple
T3780531
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Greylock Partners |
E85404
|
entity |
| Predicate | investment |
P20646
|
FINISHED |
| Object | Okta |
E292745
|
NE 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: Okta | Statement: [Greylock Partners, investment, Okta]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Okta Context triple: [Greylock Partners, investment, Okta]
-
A.
Okta
chosen
Okta is a cloud-based identity and access management platform that provides secure single sign-on, authentication, and user management for applications and services.
-
B.
Duo Security
Duo Security is a cybersecurity company best known for its cloud-based multi-factor authentication and zero-trust access solutions.
-
C.
Zscaler
Zscaler is a cloud-based information security company known for providing secure access and zero-trust networking solutions to enterprises worldwide.
-
D.
Microsoft Entra
Microsoft Entra is Microsoft’s unified identity and access management product family that secures access to applications, resources, and digital identities across cloud and hybrid environments.
-
E.
MuleSoft
MuleSoft is an integration and API management platform that helps organizations connect applications, data, and devices across cloud and on-premises environments.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69aed937fa8881908208ef3801060826 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aee3d84d7881909828903896b3cb7f |
completed | March 9, 2026, 3:14 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b4f040676c8190aa3a7952a9d6f62b |
completed | March 14, 2026, 5:21 a.m. |
Created at: March 9, 2026, 3:12 p.m.