Triple
T23859553
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Friends of Dundonald Castle |
E592403
|
entity |
| Predicate | isCharitable |
P96251
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [Friends of Dundonald Castle, isCharitable, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isCharitable Context triple: [Friends of Dundonald Castle, isCharitable, true]
-
A.
isCharity
chosen
Indicates that an entity operates as a charitable organization or is recognized as a charity.
-
B.
hasCharitableComponent
Indicates that something includes or is associated with a charitable element, such as donations, philanthropy, or support for a charitable cause.
-
C.
isPhilanthropic
Indicates that an entity habitually engages in generous actions or donations intended to promote the welfare of others.
-
D.
hasCharitableFunction
Indicates that an entity performs or is designated to perform activities intended for charitable purposes or public benefit.
-
E.
hasCharitableOrigins
Indicates that something originates from, was founded by, or is fundamentally based on charitable purposes, activities, or organizations.
- 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_69e25d22eb488190914b193aff952e83 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1cadebc6481909110a2a5fe85c93f |
completed | April 29, 2026, 9:09 a.m. |
| PD | Predicate disambiguation | batch_69f1614612b481908c45d99e588882f9 |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 8:12 p.m.