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.