Triple
T10993916
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ben Horowitz |
E259814
|
entity |
| Predicate | previousWorkplace |
P1910
|
FINISHED |
| Object | Loudcloud |
E47369
|
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: Loudcloud | Statement: [Ben Horowitz, previousWorkplace, Loudcloud]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Loudcloud Context triple: [Ben Horowitz, previousWorkplace, Loudcloud]
-
A.
Loudcloud
chosen
Loudcloud was a pioneering early-2000s cloud and managed hosting company co-founded by Marc Andreessen that later evolved into the software firm Opsware.
-
B.
Rackspace
Rackspace is a cloud computing company known for co-founding and helping develop the OpenStack open-source cloud platform.
-
C.
DigitalOcean
DigitalOcean is a cloud infrastructure provider known for its simple, developer-friendly platform offering virtual servers, storage, and networking services.
-
D.
Tucows
Tucows is a Canadian internet services company best known as a major domain name registrar and provider of related web and email services.
-
E.
Akamai Technologies
Akamai Technologies is a leading global content delivery network (CDN) and cloud services provider that optimizes and secures the delivery of online content and applications.
- 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_69d6aa8a6a548190a750f944ccdc8064 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d795d460d88190bff918d6dfdb0f93 |
completed | April 9, 2026, 12:04 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e3451451988190add2762b1e1be8ed |
completed | April 18, 2026, 8:47 a.m. |
Created at: April 8, 2026, 9:24 p.m.