Triple
T144132
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rory John Gates |
E2915
|
entity |
| Predicate | publicProfile |
P5387
|
FINISHED |
| Object | keeps social media presence limited |
—
|
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: keeps social media presence limited | Statement: [Rory John Gates, publicProfile, keeps social media presence limited]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: publicProfile Context triple: [Rory John Gates, publicProfile, keeps social media presence limited]
-
A.
publicAccess
Indicates that something is available for use, entry, or viewing by the general public without special restrictions or permissions.
-
B.
primaryUser
Indicates that the referenced user is the main or principal user associated with a given account, resource, or context.
-
C.
fullName
Indicates that an entity has a complete personal name, typically combining given name(s) and family name into a single string.
-
D.
popularFor
Indicates that something is widely liked, recognized, or favored specifically because of a particular feature, quality, or use.
-
E.
export
Indicates that one entity sends goods, services, or data out from its own domain or territory to another entity or external destination.
- 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.