Triple
T18302041
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | U Sports |
E438379
|
entity |
| Predicate | hasSubdivision |
P747
|
FINISHED |
| Object | AUS |
—
|
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: AUS | Statement: [U Sports, hasSubdivision, AUS]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: AUS Context triple: [U Sports, hasSubdivision, AUS]
-
A.
AUS
chosen
AUS is the governing body for university-level varsity sports in Atlantic Canada, organizing intercollegiate athletic competitions among its member institutions.
-
B.
AUS
AUS is the three-letter country code for Australia, the host nation of the 2000 Summer Olympics in Sydney.
-
C.
AUS
AUS is the three-letter IATA airport code for Austin–Bergstrom International Airport, the primary commercial airport serving Austin, Texas.
-
D.
AU
Aarhus University (AU) is a major public research university in Aarhus, Denmark, known for its broad range of academic programs and strong international profile.
-
E.
AU
AU is the commonly used abbreviation for Anna University, a prominent public technical university based in Chennai, India.
- 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_69d8b915e3e881909125d760c15d0c29 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e50180ac48819090e9a8f11ba10c3d |
completed | April 19, 2026, 4:23 p.m. |
Created at: April 10, 2026, 10:35 a.m.