Triple
T25891216
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Café in the Crypt |
E652337
|
entity |
| Predicate | revenueSupports |
P9389
|
FINISHED |
| Object | homelessness projects |
—
|
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: homelessness projects | Statement: [Café in the Crypt, revenueSupports, homelessness projects]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: revenueSupports Context triple: [Café in the Crypt, revenueSupports, homelessness projects]
-
A.
revenue
Indicates the amount of income generated by an entity from its business activities or operations over a specified period.
-
B.
revenueLevel
Indicates the relative amount or tier of revenue associated with an entity or activity.
-
C.
providesSupportTo
Indicates that one entity offers help, resources, or reinforcement to another entity to aid its function, stability, or success.
-
D.
revenueUse
chosen
Indicates how generated revenue is allocated, spent, or applied toward specific purposes or activities.
-
E.
revenueSources
Indicates the relationship identifying where an entity’s revenue comes from or the different streams that generate its income.
- 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_69e7ab3c6cc081908de59bfcc28ec19d |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f6037eab948190b1e16f6f0a8697cc |
completed | May 2, 2026, 2 p.m. |
| PD | Predicate disambiguation | batch_69f5afec3e94819080d9ba86cf8c866e |
completed | May 2, 2026, 8:03 a.m. |
Created at: April 22, 2026, 8:21 a.m.