Triple
T1105338
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Charles Foster |
E25475
|
entity |
| Predicate | privacyStatus |
P15689
|
FINISHED |
| Object | kept largely out of the public eye |
—
|
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: kept largely out of the public eye | Statement: [Charles Foster, privacyStatus, kept largely out of the public eye]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: privacyStatus Context triple: [Charles Foster, privacyStatus, kept largely out of the public eye]
-
A.
privacyProperty
Indicates that one entity has a characteristic, rule, or condition specifically related to privacy in the context of the relationship.
-
B.
privacyCharacteristic
chosen
Indicates the specific privacy-related property or feature that characterizes how information is handled, protected, or exposed in a given context.
-
C.
copyrightStatus
Indicates the legal protection state of a work, specifying whether and how it is covered by copyright.
-
D.
protectionLevel
Indicates the degree or extent to which something is safeguarded against harm, risk, or unauthorized access.
-
E.
dataPolicy
Indicates that one entity defines or governs how data related to another entity is collected, used, stored, or shared.
- 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_69a49428d4448190b3b36991ceae87ce |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4b9e21f048190bf4b63dd2c7c7641 |
completed | March 1, 2026, 10:12 p.m. |
| PD | Predicate disambiguation | batch_69a4b74877748190b78cd8847ee4fa7a |
completed | March 1, 2026, 10:01 p.m. |
Created at: March 1, 2026, 7:43 p.m.