Triple
T32283610
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MetLife Foundation Award for Medical Research |
E824764
|
entity |
| Predicate | sponsorIndustryBackground |
P107176
|
FINISHED |
| Object | insurance |
—
|
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: insurance | Statement: [MetLife Foundation Award for Medical Research, sponsorIndustryBackground, insurance]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sponsorIndustryBackground Context triple: [MetLife Foundation Award for Medical Research, sponsorIndustryBackground, insurance]
-
A.
sponsorIndustry
Indicates that an entity acts as a sponsor for, or is financially or organizationally supporting, a particular industry or industrial sector.
-
B.
sponsorshipIndustry
chosen
Indicates a relationship where one entity sponsors another specifically within a given industry or sector context.
-
C.
supportedIndustry
Indicates that one entity provides backing, resources, or services to help sustain or advance a particular industry.
-
D.
stakeholderIndustry
Indicates the industry or sector in which a stakeholder operates or is primarily involved.
-
E.
associatedIndustrySite
Indicates that one entity is linked or related to another entity that represents an industry-specific website or online resource.
- 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_69f3490f404081908450db66884f4334 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6f8164698819090c1b471f1caa4c6 |
completed | May 3, 2026, 7:24 a.m. |
| PD | Predicate disambiguation | batch_69f6f6619404819084662aef1238261c |
completed | May 3, 2026, 7:16 a.m. |
Created at: May 1, 2026, 12:43 a.m.