Triple
T38372099
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | murder of George Floyd |
E892611
|
entity |
| Predicate | durationOfRestraint |
P190809
|
FINISHED |
| Object | approximately 9 minutes 29 seconds |
—
|
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: approximately 9 minutes 29 seconds | Statement: [murder of George Floyd, durationOfRestraint, approximately 9 minutes 29 seconds]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: durationOfRestraint Context triple: [murder of George Floyd, durationOfRestraint, approximately 9 minutes 29 seconds]
-
A.
durationOfDetention
Indicates the length of time that an entity is or was held in detention.
-
B.
restraintType
Indicates the specific kind or method of restraint applied in a given situation or relationship.
-
C.
durationOfImprisonment
Indicates the length of time that an entity is or was held in imprisonment.
-
D.
restraintManufacturer
Indicates that one entity is the manufacturer or producer of a restraint device used to limit or control another entity.
-
E.
restraintPurpose
Indicates that one entity is used to restrain another entity for a specific purpose or intended outcome.
- F. None of above. chosen
Provenance (4 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_69f76e47cb4c8190bdd92cd1db59c0c5 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fcd1499e2c81909bafd84dc4810f45 |
completed | May 7, 2026, 5:52 p.m. |
| PD | Predicate disambiguation | batch_69fcccf024ec819086383ffbb6cfc036 |
completed | May 7, 2026, 5:33 p.m. |
| PDg | Predicate description generation | batch_69fcd148e6d4819082c118832ecc599b |
completed | May 7, 2026, 5:52 p.m. |
Created at: May 3, 2026, 4:31 p.m.