Triple
T38430821
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thrive Capital |
E903792
|
entity |
| Predicate | hasPortfolioCompany |
P43497
|
FINISHED |
| Object |
—
|
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: Instagram | Statement: [Thrive Capital, hasPortfolioCompany, Instagram]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPortfolioCompany Context triple: [Thrive Capital, hasPortfolioCompany, Instagram]
-
A.
portfolioCompany
chosen
Indicates that one entity is a company in which another entity (typically an investor or investment fund) holds an ownership stake as part of its investment portfolio.
-
B.
hasVentureCapitalPresence
Indicates that a venture capital firm or investment activity is present, involved, or operating in relation to the specified entity.
-
C.
portfolioHeldBy
Indicates that a particular portfolio is owned, managed, or maintained by a specified entity.
-
D.
portfolioHolderTitle
Indicates the formal title or designation held by the person or entity that owns or manages the portfolio.
-
E.
hasCompanyName
Indicates that an entity is associated with or identified by a specific company name.
- 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_69f76e6a2024819081aa04f4932f89d2 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a00119d821c8190874786391b27ef23 |
completed | May 10, 2026, 5:03 a.m. |
| PD | Predicate disambiguation | batch_6a001143fb6881909ac0ae8bfea04351 |
completed | May 10, 2026, 5:01 a.m. |
Created at: May 3, 2026, 4:31 p.m.