Triple
T123453
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Southern Research |
E2494
|
entity |
| Predicate | hasNonprofitStatus |
P70
|
FINISHED |
| Object | 501(c)(3) |
—
|
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: 501(c)(3) | Statement: [Southern Research, hasNonprofitStatus, 501(c)(3)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNonprofitStatus Context triple: [Southern Research, hasNonprofitStatus, 501(c)(3)]
-
A.
nonprofitStatus
chosen
Indicates that an entity operates as a nonprofit organization, typically meeting legal or regulatory criteria for nonprofit status.
-
B.
hasLegalStatus
Indicates that an entity possesses a particular legal classification, recognition, or standing under law.
-
C.
isCharterMemberOf
Indicates that an entity is an original or founding member of a group, organization, or institution at the time it was established.
-
D.
hasTypeOfOrganization
Indicates that an entity is classified as belonging to a particular type or category of organization.
-
E.
hasMainGoverningBody
Indicates that an entity possesses a primary official organization or authority responsible for its overall governance or decision-making.
- 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_69a251b54ea88190b18281669f59b4c0 |
completed | Feb. 28, 2026, 2:23 a.m. |
| NER | Named-entity recognition | batch_69a2573ce0ac8190b49fb31d3d475bf9 |
completed | Feb. 28, 2026, 2:47 a.m. |
| PD | Predicate disambiguation | batch_69a2564928208190966a619680a0d6e2 |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:27 a.m.