Triple
T21996885
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | INTOSAI |
E543228
|
entity |
| Predicate | standardAbbreviation |
P43
|
FINISHED |
| Object | ISSAI |
—
|
NE NERFINISHED |
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: ISSAI | Statement: [INTOSAI, standardAbbreviation, ISSAI]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: ISSAI Context triple: [INTOSAI, standardAbbreviation, ISSAI]
-
A.
OISS
OISS is the ICAO airport code for Shiraz International Airport in Shiraz, Iran.
-
B.
ISAS
ISAS (Institute of Space and Astronautical Science) is a Japanese research institute specializing in space and planetary science, now part of the Japan Aerospace Exploration Agency (JAXA).
-
C.
ISSAI framework
chosen
The ISSAI framework is a comprehensive set of professional standards and guidelines that define best practices for public-sector auditing worldwide.
-
D.
ISSP
ISSP is a renowned research institute of the University of Tokyo specializing in condensed matter and solid state physics.
-
E.
ISS
ISS is an acronym commonly used to refer to Information Systems and Services, the organizational function responsible for managing and supporting an institution’s information technology infrastructure and services.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e11e2c814c8190837d072789000486 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f12765fb0c81908f7b7acda065ee2f |
completed | April 28, 2026, 9:32 p.m. |
Created at: April 16, 2026, 8:19 p.m.