Triple
T804756
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | L2M |
E17403
|
entity |
| Predicate | organizationTypeOfSponsor |
P2589
|
FINISHED |
| Object | U.S. government research agency |
—
|
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: U.S. government research agency | Statement: [L2M, organizationTypeOfSponsor, U.S. government research agency]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: organizationTypeOfSponsor Context triple: [L2M, organizationTypeOfSponsor, U.S. government research agency]
-
A.
sponsoringOrganizationType
chosen
Indicates the kind or category of organization that provides sponsorship or support in the described relationship or activity.
-
B.
organizationType
Indicates the specific category or classification of an organization in terms of its nature, structure, or primary function.
-
C.
responsibleOrganizationType
Indicates the type or category of organization that holds responsibility for a given action, resource, or obligation.
-
D.
sponsoringInstitution
Indicates that an institution provides financial or organizational support to enable or underwrite an activity, project, event, or entity.
-
E.
parentOrganizationType
Indicates the classification or category of the organization that serves as the parent in a hierarchical relationship.
- 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_69a4937ae8a08190b5084a03d532b30e |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4ace495348190aec66f35ea90bc89 |
completed | March 1, 2026, 9:17 p.m. |
| PD | Predicate disambiguation | batch_69a4aa70973c8190adbf08302d1103a9 |
completed | March 1, 2026, 9:06 p.m. |
Created at: March 1, 2026, 7:38 p.m.