Triple
T6880659
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Selwyn College Boat Club |
E158785
|
entity |
| Predicate | competesIn |
P2440
|
FINISHED |
| Object | Lent Bumps |
E321094
|
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: Lent Bumps | Statement: [Selwyn College Boat Club, competesIn, Lent Bumps]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lent Bumps Context triple: [Selwyn College Boat Club, competesIn, Lent Bumps]
-
A.
Lent Bumps
chosen
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.
-
B.
May Bumps
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.
-
C.
Ba Bump
"Ba Bump" is a song by the American hip hop group The Black Eyed Peas from their 2005 album "Monkey Business."
-
D.
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.
-
E.
Bump It
"Bump It" is a funk- and soul-infused track by Erykah Badu from her 2003 album *Worldwide Underground*, known for its laid-back groove and extended jam feel.
- 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_69c688342f6c8190ad7eea6ba262db99 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d8e798c08190b1f494a2c1445514 |
completed | March 27, 2026, 7:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c742c999cc8190a14aa0ae6c7a1f54 |
completed | March 28, 2026, 2:54 a.m. |
Created at: March 27, 2026, 2:23 p.m.