Triple
T16116423
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | UfM Senior Officials |
E391011
|
entity |
| Predicate | followsUpOn |
P32415
|
FINISHED |
| Object | UfM policy decisions |
—
|
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: UfM policy decisions | Statement: [UfM Senior Officials, followsUpOn, UfM policy decisions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: followsUpOn Context triple: [UfM Senior Officials, followsUpOn, UfM policy decisions]
-
A.
followsUp
chosen
Indicates that one entity continues, responds to, or builds upon a previous entity, typically as a subsequent action, communication, or step.
-
B.
followUpType
Indicates the specific category or nature of a follow-up action or interaction that occurs after an initial event or communication.
-
C.
follows
Indicates that one entity comes after, moves behind, or acts in accordance with another entity in time, space, or sequence.
-
D.
followUpMechanism
Indicates a mechanism or process that is used to continue, monitor, or respond to a prior action, event, or communication.
-
E.
followUpRelease
Indicates that one release occurs subsequently as a continuation or update to a previous release.
- 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_69d87f1a8dd881909f1de6ef78849874 |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e2016b5c948190b0f1eccb97ee85cc |
completed | April 17, 2026, 9:46 a.m. |
| PD | Predicate disambiguation | batch_69e1828518c48190a8ef3aaa46a1f639 |
completed | April 17, 2026, 12:44 a.m. |
Created at: April 10, 2026, 5 a.m.