Triple
T843082
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dustin Moskovitz |
E18217
|
entity |
| Predicate | coFoundedOrganizationType |
P5179
|
FINISHED |
| Object | social media company |
—
|
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: social media company | Statement: [Dustin Moskovitz, coFoundedOrganizationType, social media company]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: coFoundedOrganizationType Context triple: [Dustin Moskovitz, coFoundedOrganizationType, social media company]
-
A.
foundedOrganizationType
chosen
Indicates that an entity established or created an organization of a specified type (e.g., company, nonprofit, institution).
-
B.
foundedOrganization
Indicates that an entity established or created an organization.
-
C.
foundingOrganization
Indicates the organization that established or created another entity, such as a company, institution, or project.
-
D.
organizationFounded
Indicates that an organization was established or created at a specific point in time, often by a particular founder or founding entity.
-
E.
organizationType
Indicates the specific category or classification of an organization in terms of its nature, structure, or primary function.
- 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_69a4938b04208190b82e1df6b572c548 |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4abe8a0bc81909b54af465e67be1f |
completed | March 1, 2026, 9:13 p.m. |
| PD | Predicate disambiguation | batch_69a4aa7f396c8190aa8b8dfbe0b4f732 |
completed | March 1, 2026, 9:07 p.m. |
Created at: March 1, 2026, 7:38 p.m.