Triple
T19117658
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | UGC 5923 |
E467946
|
entity |
| Predicate | catalog |
P20407
|
FINISHED |
| Object | UGC |
—
|
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: UGC | Statement: [UGC 5923, catalog, UGC]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: UGC Context triple: [UGC 5923, catalog, UGC]
-
A.
UGC
UGC (University Grants Commission) is a statutory body of the Indian government responsible for coordinating, determining, and maintaining standards of higher education in India.
-
B.
UGC
chosen
UGC is an astronomical catalog of galaxies widely used to identify and classify extragalactic objects such as the Leo II Dwarf Galaxy.
-
C.
UGC
UGC is the national higher education regulatory and funding body of Bangladesh responsible for overseeing universities and maintaining academic standards.
-
D.
UGC
UGC is the statutory body in Hong Kong responsible for advising the government on the funding and strategic development of publicly funded universities.
-
E.
UGC
UGC is a major French film production and distribution company, also known for operating a large chain of cinemas in France and other European countries.
- 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_69d8dd06a26481908039e2a1bae8c597 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e399a6d8819090a9501ff1637b9d |
completed | April 20, 2026, 8:28 a.m. |
Created at: April 10, 2026, 12:05 p.m.