Triple
T6179096
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Charles Simonyi |
E137892
|
entity |
| Predicate | acquisitionOfCompany |
P2511
|
FINISHED |
| Object | Intentional Software acquired by Microsoft in 2017 |
—
|
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: Intentional Software acquired by Microsoft in 2017 | Statement: [Charles Simonyi, acquisitionOfCompany, Intentional Software acquired by Microsoft in 2017]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: acquisitionOfCompany Context triple: [Charles Simonyi, acquisitionOfCompany, Intentional Software acquired by Microsoft in 2017]
-
A.
acquiredCompany
Indicates that one entity has purchased and taken ownership or control of another company.
-
B.
acquisition
chosen
Indicates the act or relationship in which one entity obtains ownership or control of another entity, asset, or resource.
-
C.
tookOverCompanyFrom
Indicates that one entity assumed control or ownership of a company previously controlled or owned by another entity.
-
D.
acquisitionResultedIn
Indicates that an acquisition event led to a particular outcome, state, or consequence for the involved entities.
-
E.
laterAcquiredBy
Indicates that one entity was acquired by another entity at a later point in time, after some prior state or ownership.
- 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_69c008a80f748190ba3d07ffc81acb29 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c05dcb77948190b5385438f81bf0a8 |
completed | March 22, 2026, 9:23 p.m. |
| PD | Predicate disambiguation | batch_69c055fa0a808190bda37832e3ac150c |
completed | March 22, 2026, 8:50 p.m. |
Created at: March 22, 2026, 4:18 p.m.