Triple
T3572421
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wisconsin Institutes for Discovery |
E75603
|
entity |
| Predicate | engagesAudience |
P45833
|
FINISHED |
| Object | university researchers |
—
|
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: university researchers | Statement: [Wisconsin Institutes for Discovery, engagesAudience, university researchers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: engagesAudience Context triple: [Wisconsin Institutes for Discovery, engagesAudience, university researchers]
-
A.
hasAudienceParticipation
chosen
Indicates that an event, performance, or activity involves direct participation or interaction from the audience.
-
B.
engagementLevel
Indicates the degree or intensity of involvement, interest, or participation one entity has in relation to another entity, activity, or context.
-
C.
engagementCapability
Indicates the ability or capacity of one entity to initiate, conduct, or sustain an interaction or engagement with another entity.
-
D.
engagementArea
Indicates the spatial region or scope within which an entity’s actions, influence, or interactions are intended to occur.
-
E.
engagementPhase
Indicates the specific stage or phase an ongoing interaction, project, or relationship is currently in within its overall lifecycle.
- 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_69ad85d5e3008190bdfe0bacdd1f5a1b |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc0c447fc81909689259558187af4 |
completed | March 8, 2026, 6:32 p.m. |
| PD | Predicate disambiguation | batch_69adb8364d848190a96a9bc7a6126af2 |
completed | March 8, 2026, 5:56 p.m. |
Created at: March 8, 2026, 3:21 p.m.