Triple
T12373029
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aaron Levie |
E295049
|
entity |
| Predicate | startupStageExperience |
P22109
|
FINISHED |
| Object | early-stage technology startups |
—
|
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: early-stage technology startups | Statement: [Aaron Levie, startupStageExperience, early-stage technology startups]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: startupStageExperience Context triple: [Aaron Levie, startupStageExperience, early-stage technology startups]
-
A.
providesExperienceOf
Indicates that one entity enables or delivers the experience of another entity to someone or something.
-
B.
primaryExperience
Indicates that one entity is the main or most significant experience associated with another entity, as opposed to secondary or supporting experiences.
-
C.
documentsCareerStage
Indicates that something records or specifies the career stage or professional phase of an entity.
-
D.
supportsCareerStage
Indicates that one entity provides resources, opportunities, or conditions that are appropriate or beneficial for another entity’s specific stage in their career.
-
E.
experienceType
chosen
Indicates the specific kind or category of experience associated with an entity or event.
- 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_69d6ab6d8a4081908636601e69ddf262 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d942a2d6e08190a13c7ff89af09354 |
completed | April 10, 2026, 6:34 p.m. |
| PD | Predicate disambiguation | batch_69d93ecf6b548190a394b6b56a0c1c68 |
completed | April 10, 2026, 6:17 p.m. |
Created at: April 8, 2026, 9:54 p.m.