Triple
T3685489
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Peterhouse Boat Club |
E78213
|
entity |
| Predicate | competition |
P563
|
FINISHED |
| Object | May Bumps |
E321093
|
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: May Bumps | Statement: [Peterhouse Boat Club, competition, May Bumps]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: May Bumps Context triple: [Peterhouse Boat Club, competition, May Bumps]
-
A.
May Bumps
chosen
May Bumps is an annual series of rowing races held on the River Cam in Cambridge, featuring college crews competing in a distinctive bumps race format.
-
B.
Ba Bump
"Ba Bump" is a song by the American hip hop group The Black Eyed Peas from their 2005 album "Monkey Business."
-
C.
Bump, Bump, Bump
"Bump, Bump, Bump" is an early-2000s R&B/hip-hop single by B2K featuring R. Kelly that became a commercial hit and club favorite.
-
D.
Lent Bumps
Lent Bumps is a traditional annual series of bumps rowing races held on the River Cam in Cambridge, primarily contested by the university’s college boat clubs.
-
E.
M-Maybe
M-Maybe is a famous 1965 pop art painting by Roy Lichtenstein that depicts a comic book-style blonde woman in a moment of suspense, exemplifying his signature use of Ben-Day dots and bold outlines.
- 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_69ad85e285a081908f8cbfa9e2ed9b75 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc4c49b408190bc800bcf9745fe4f |
completed | March 8, 2026, 6:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b4c3bd473c8190b814689f3c76cada |
completed | March 14, 2026, 2:11 a.m. |
Created at: March 8, 2026, 3:26 p.m.