Triple
T18972760
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | AUT Business School |
E464211
|
entity |
| Predicate | acronym |
P43
|
FINISHED |
| Object | AUT |
—
|
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: AUT | Statement: [AUT Business School, acronym, AUT]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: AUT Context triple: [AUT Business School, acronym, AUT]
-
A.
AUT
chosen
AUT is a major New Zealand university based in Auckland, known for its focus on applied research, innovation, and industry-aligned education.
-
B.
AUT
AUT is a leading Iranian engineering and technology university, widely recognized for its strong research output and rigorous academic programs.
-
C.
Aut
Aut is a small town in the Mandi district of Himachal Pradesh, India, known as a gateway stop along the route to Kullu and Manali.
-
D.
Ath
Ath is a historic fortified town in the Wallonia region of Belgium, known for its medieval architecture and traditional annual festivals.
-
E.
ATO
ATO is Australia’s principal revenue collection agency responsible for administering the federal tax system and related superannuation laws.
- 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_69d8dd008af48190a97ff1c6488edf1b |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d61cb3ac8190bfe29104166fa090 |
completed | April 20, 2026, 7:30 a.m. |
Created at: April 10, 2026, noon