Triple
T33357767
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Clothes Off Our Back Foundation |
E854121
|
entity |
| Predicate | typeOfFundraising |
P54075
|
FINISHED |
| Object | celebrity charity auction |
—
|
LITERAL 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: celebrity charity auction | Statement: [Clothes Off Our Back Foundation, typeOfFundraising, celebrity charity auction]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfFundraising Context triple: [Clothes Off Our Back Foundation, typeOfFundraising, celebrity charity auction]
-
A.
fundraisingOutcome
Indicates the result or status of a fundraising effort, such as whether it met its goals or how successful it was.
-
B.
typeOfDonations
Indicates the kinds or categories of donations involved in a given context or transaction.
-
C.
usesFundraisingMethod
chosen
Indicates that one entity employs or applies a particular fundraising method as its means of raising funds.
-
D.
raisedMoneyFor
Indicates that one entity collected or obtained funds specifically to support or benefit another entity, cause, or purpose.
-
E.
fundraisingDescription
Indicates that a description or summary is provided for a fundraising activity, campaign, or effort involving the entities.
- F. None of above.
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_69f3496acbc8819099fd0305ecc42080 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_6a00ae638fcc819096537b2c21366161 |
completed | May 10, 2026, 4:12 p.m. |
| PD | Predicate disambiguation | batch_6a00ae0551988190bcb3564ed9af2847 |
completed | May 10, 2026, 4:10 p.m. |
Created at: May 1, 2026, 1:34 a.m.