Triple
T10975724
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 20 July plot |
E259363
|
entity |
| Predicate | intendedFollowUp |
P88492
|
FINISHED |
| Object | seizure of key government buildings in Berlin |
—
|
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: seizure of key government buildings in Berlin | Statement: [20 July plot, intendedFollowUp, seizure of key government buildings in Berlin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: intendedFollowUp Context triple: [20 July plot, intendedFollowUp, seizure of key government buildings in Berlin]
-
A.
followsUp
Indicates that one entity continues, responds to, or builds upon a previous entity, typically as a subsequent action, communication, or step.
-
B.
intendsTo
chosen
Indicates that one entity has the purpose, plan, or desire to perform an action involving another entity or outcome.
-
C.
followUpMechanism
Indicates a mechanism or process that is used to continue, monitor, or respond to a prior action, event, or communication.
-
D.
subsequentAction
Indicates that one action occurs after another in time, following it as a later step or consequence.
-
E.
followOnPhases
Indicates that certain phases occur subsequently as a continuation or next steps after preceding phases.
- 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_69d6aa895f4c8190887a15460ef622f4 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d771f4e888819097433271a2f45ff3 |
completed | April 9, 2026, 9:31 a.m. |
| PD | Predicate disambiguation | batch_69d72e8c27cc81908050590b7a04cafd |
completed | April 9, 2026, 4:43 a.m. |
Created at: April 8, 2026, 9:24 p.m.