Triple
T144130
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rory John Gates |
E2915
|
entity |
| Predicate | parentOccupation |
P5386
|
FINISHED |
| Object | Bill Gates is co-founder of Microsoft |
—
|
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: Bill Gates is co-founder of Microsoft | Statement: [Rory John Gates, parentOccupation, Bill Gates is co-founder of Microsoft]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: parentOccupation Context triple: [Rory John Gates, parentOccupation, Bill Gates is co-founder of Microsoft]
-
A.
fatherOccupation
Indicates the type of job or profession held by a person's father.
-
B.
motherOccupation
Indicates the type of job or profession that a person's mother has.
-
C.
subjectOccupation
Indicates that the subject holds or performs a particular job, profession, or role as their occupation.
-
D.
spouseOccupation
Indicates that one person’s spouse has a particular job, profession, or occupation.
-
E.
sponsorOccupation
Indicates that one entity serves as the occupation or professional role of a sponsor associated with another entity.
- F. None of above. chosen
Provenance (4 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_69a2521e35c08190b28e5c9f1e3c9b59 |
completed | Feb. 28, 2026, 2:25 a.m. |
| NER | Named-entity recognition | batch_69a257e935bc8190a03e54a10e9ba6f7 |
completed | Feb. 28, 2026, 2:50 a.m. |
| PD | Predicate disambiguation | batch_69a25656a4fc81908a87678ac3d28f93 |
completed | Feb. 28, 2026, 2:43 a.m. |
| PDg | Predicate description generation | batch_69a257101060819094db0f3a3a72f312 |
completed | Feb. 28, 2026, 2:46 a.m. |
Created at: Feb. 28, 2026, 2:31 a.m.