Triple
T15271416
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Centennial Challenges Program |
E365028
|
entity |
| Predicate | targetParticipant |
P30745
|
FINISHED |
| Object | small businesses |
—
|
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: small businesses | Statement: [Centennial Challenges Program, targetParticipant, small businesses]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: targetParticipant Context triple: [Centennial Challenges Program, targetParticipant, small businesses]
-
A.
participantFrom
chosen
Indicates that a participant originates from, is associated with, or comes out of a specified source, group, or context.
-
B.
participant
Indicates that an entity takes part in, is involved in, or plays a role within a specified event, activity, or process.
-
C.
targetOwner
Indicates that one entity is the owner or primary possessor of a specified target entity.
-
D.
primaryParticipant
Indicates that an entity plays the main or most central role in a given event, activity, or relationship.
-
E.
determinesParticipantIn
Indicates that one entity has the authority or role to decide or specify which other entity (or entities) will participate in a given event, activity, or process.
- 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_69d85a0f08408190b3c3259ae35d79d2 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e0094eac848190a1740ae1aa6b28e0 |
completed | April 15, 2026, 9:55 p.m. |
| PD | Predicate disambiguation | batch_69deca90739081909bd1b797cdb8af2b |
completed | April 14, 2026, 11:15 p.m. |
Created at: April 10, 2026, 3:14 a.m.