Triple
T21483211
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sean Ellis |
E530046
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Cashback |
—
|
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: Cashback | Statement: [Sean Ellis, notableWork, Cashback]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cashback Context triple: [Sean Ellis, notableWork, Cashback]
-
A.
Cashback
chosen
"Cashback" is a British romantic comedy-drama film, expanded from Sean Ellis's Oscar-nominated short, about an art student who copes with insomnia by imagining time stopping during his late-night supermarket shifts.
-
B.
Rewards4All
Rewards4All was Flybe’s frequent-flyer loyalty program that allowed passengers to earn and redeem points for flights and related travel benefits.
-
C.
Real Rewards
Real Rewards is American Eagle Outfitters’ customer loyalty program that offers members points, discounts, and exclusive benefits for shopping with the brand.
-
D.
GrabRewards
GrabRewards is Grab’s loyalty program that lets users earn and redeem points for discounts, services, and partner offers across the Grab ecosystem.
-
E.
Copons
Copons is a small municipality in the Anoia comarca of Catalonia, Spain, known for its rural character and historic architecture.
- 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_69e0c45acc3881908e38d3f28964152b |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9ea34c4388190adc78d209d2aafb8 |
completed | April 23, 2026, 9:45 a.m. |
Created at: April 16, 2026, 6:21 p.m.