Triple
T13084375
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cal |
E310291
|
entity |
| Predicate | abbreviation |
P43
|
FINISHED |
| Object | UCB |
E399679
|
NE 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: UCB | Statement: [Cal, abbreviation, UCB]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: UCB Context triple: [Cal, abbreviation, UCB]
-
A.
UCB
chosen
UCB is a specialist university in Birmingham, England, known for its vocational and professional courses in areas such as hospitality, tourism, and culinary arts.
-
B.
CUC
CUC is the national organization representing Unitarian and Unitarian Universalist congregations across Canada, providing support, resources, and coordination for their religious and social justice activities.
-
C.
UCI
UCI is the international governing body for cycling, responsible for overseeing competitive cycling events and setting global rules and standards for the sport.
-
D.
UCE
UCE is a major public university in Quito, Ecuador, recognized as one of the country’s oldest and most important higher education institutions.
-
E.
UC
UC is the final generation of the Holden Torana, a compact Australian car produced in the late 1970s.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d806a733548190989cfd4ce981ca33 |
completed | April 9, 2026, 8:05 p.m. |
| NER | Named-entity recognition | batch_69d981361e8c819099376435aa3a7aa3 |
completed | April 10, 2026, 11:01 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6d61060188190911eb3e135dc25ac |
completed | May 3, 2026, 4:58 a.m. |
Created at: April 9, 2026, 9:02 p.m.