Triple
T5098244
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Devine |
E114918
|
entity |
| Predicate | associatedWithPrisonerProtest |
P56130
|
FINISHED |
| Object | blanket protest |
—
|
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: blanket protest | Statement: [Michael Devine, associatedWithPrisonerProtest, blanket protest]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedWithPrisonerProtest Context triple: [Michael Devine, associatedWithPrisonerProtest, blanket protest]
-
A.
associatedWithPrisonProtest
chosen
Indicates a relationship where an entity is connected to, involved in, or linked with a protest occurring within or related to a prison context.
-
B.
postPrisonOccupation
Indicates the type of work or occupation a person engages in after being released from prison.
-
C.
notableProtest
Indicates that an entity is recognized for having led, organized, or been centrally involved in a significant protest or demonstration.
-
D.
teamDuringProtest
Indicates that two or more entities are part of the same team or organized group specifically in the context of a protest event.
-
E.
hasPrisoners
Indicates that an entity holds or contains one or more individuals who are imprisoned or detained.
- 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_69bd443fc49c819089629c00e311310c |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd7567d21081909227ed8f08b74c71 |
completed | March 20, 2026, 4:27 p.m. |
| PD | Predicate disambiguation | batch_69bd715e06808190931934dc9930f997 |
completed | March 20, 2026, 4:10 p.m. |
Created at: March 20, 2026, 1:40 p.m.