Triple
T28441515
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Margarethe Krupp |
E715722
|
entity |
| Predicate | type of philanthropic work |
P3801
|
FINISHED |
| Object | housing |
—
|
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: housing | Statement: [Margarethe Krupp, type of philanthropic work, housing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: type of philanthropic work Context triple: [Margarethe Krupp, type of philanthropic work, housing]
-
A.
genreOfPhilanthropy
chosen
Indicates the specific type or category of philanthropic activity to which an act, initiative, or organization belongs.
-
B.
philanthropicInitiative
Indicates an action or relationship where an entity undertakes or supports activities intended to promote the welfare of others, typically through charitable or socially beneficial efforts.
-
C.
fieldOfPhilanthropy
Indicates that an entity is engaged in or associated with a particular area or domain of philanthropic activity.
-
D.
isPhilanthropic
Indicates that an entity habitually engages in generous actions or donations intended to promote the welfare of others.
-
E.
philanthropicDonation
Indicates that one entity voluntarily gives money, goods, or services to another entity for charitable or public-benefit purposes without expecting direct compensation.
- 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_69efd6b44550819094ae991b553d9fc3 |
completed | April 27, 2026, 9:35 p.m. |
| NER | Named-entity recognition | batch_69f64e3da3908190a38f80a9fe4cadba |
completed | May 2, 2026, 7:19 p.m. |
| PD | Predicate disambiguation | batch_69f64caede108190a35cc7cbfead866f |
completed | May 2, 2026, 7:12 p.m. |
Created at: April 28, 2026, 1:46 a.m.