Triple
T13889537
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | BPS-3 |
E333932
|
entity |
| Predicate | leaveEntitlement |
P54319
|
FINISHED |
| Object | as per civil service leave rules of Pakistan |
—
|
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: as per civil service leave rules of Pakistan | Statement: [BPS-3, leaveEntitlement, as per civil service leave rules of Pakistan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: leaveEntitlement Context triple: [BPS-3, leaveEntitlement, as per civil service leave rules of Pakistan]
-
A.
leaveType
Indicates the type or category of leave associated with an absence or time-off event (e.g., vacation, sick leave, parental leave).
-
B.
leaveProtection
Indicates that an entity stops providing protection or removes a protective status from another entity.
-
C.
standardForLeave
chosen
Indicates that something defines, specifies, or serves as the normative basis or criteria for granting or taking leave.
-
D.
coveredReasonForLeave
Indicates that a specified reason for leave is included under and qualifies for coverage within a particular leave policy or program.
-
E.
releaseOfWork
Indicates that one entity makes a work (such as a product, publication, or creative output) publicly available or officially issued.
- 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_69d81c5dd2d48190b7a5fc1e009de936 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de23a3a24881908d81d634622fbbcc |
completed | April 14, 2026, 11:23 a.m. |
| PD | Predicate disambiguation | batch_69dd464b1ab48190ae50bfc902bf6ef7 |
completed | April 13, 2026, 7:38 p.m. |
Created at: April 9, 2026, 10:15 p.m.