Triple
T24931370
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ronit Krushka |
E618995
|
entity |
| Predicate | leavesCommunity |
P157246
|
FINISHED |
| Object | to live a secular life |
—
|
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: to live a secular life | Statement: [Ronit Krushka, leavesCommunity, to live a secular life]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: leavesCommunity Context triple: [Ronit Krushka, leavesCommunity, to live a secular life]
-
A.
community
Indicates a relationship where individuals or groups are connected by shared location, interests, or identity, forming a collective social unit.
-
B.
leavesEmployer
Indicates that an employee ends or terminates their working relationship with an employer.
-
C.
isCommunityOf
Indicates that one entity functions as a community composed of, or defined by, the members or elements represented by the other entity.
-
D.
hasCommunityIn
Indicates that a community is present, active, or established within a specified location, platform, or context.
-
E.
leaveProtection
Indicates that an entity stops providing protection or removes a protective status from 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_69e2fab9edd88190b86004a78a28bc20 |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f423b49074819095c7df8610781661 |
completed | May 1, 2026, 3:53 a.m. |
| PD | Predicate disambiguation | batch_69f4210130d08190ae30b7943f7a0bbc |
completed | May 1, 2026, 3:41 a.m. |
| PDg | Predicate description generation | batch_69f423637bec8190a1701421ac86a3b7 |
completed | May 1, 2026, 3:52 a.m. |
Created at: April 18, 2026, 5:30 a.m.