Triple
T8973578
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bethesda Orphanage |
E214326
|
entity |
| Predicate | charitableFunction |
P56346
|
FINISHED |
| Object | orphan care |
—
|
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: orphan care | Statement: [Bethesda Orphanage, charitableFunction, orphan care]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: charitableFunction Context triple: [Bethesda Orphanage, charitableFunction, orphan care]
-
A.
hasCharitableFunction
chosen
Indicates that an entity performs or is designated to perform activities intended for charitable purposes or public benefit.
-
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.
charityComponent
Indicates that one entity functions as a charitable element, feature, or part within another entity or larger arrangement.
-
D.
associatedCharity
Indicates that one entity has a formal or recognized charitable affiliation or partnership with another entity.
-
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_69ca839dbf608190a2f5990477115d29 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc6783abe48190840e652fc2acf28f |
completed | April 1, 2026, 12:32 a.m. |
| PD | Predicate disambiguation | batch_69cc5ed9a2d48190ad11381078e823b7 |
completed | March 31, 2026, 11:55 p.m. |
Created at: March 30, 2026, 7:02 p.m.