Triple
T32410492
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | U.S. Department of Justice civil rights investigation (2015) |
E828204
|
entity |
| Predicate | typeOfMisconductAlleged |
P198859
|
FINISHED |
| Object | civil rights violations |
—
|
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: civil rights violations | Statement: [U.S. Department of Justice civil rights investigation (2015), typeOfMisconductAlleged, civil rights violations]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfMisconductAlleged Context triple: [U.S. Department of Justice civil rights investigation (2015), typeOfMisconductAlleged, civil rights violations]
-
A.
hasTypeOfMisconduct
chosen
Indicates that an entity is associated with a specific category or kind of misconduct.
-
B.
allegedMisconductLocation
Indicates the place where the alleged misconduct is reported to have occurred.
-
C.
typeOfOffenseAddressed
Indicates the specific category or kind of offense that a given action, measure, or legal provision is intended to address.
-
D.
accusationType
Indicates the specific category or nature of an accusation made by one party against another.
-
E.
allegedWrongdoingByOthers
Indicates that someone claims or asserts that other entities have engaged in wrongful or improper behavior.
- 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_69f34919f300819092b541c6277cd68a |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_6a0059f4ffe481908dc500cee9051148 |
completed | May 10, 2026, 10:12 a.m. |
| PD | Predicate disambiguation | batch_6a00593a3c1881909b2ff1a29eb474b3 |
completed | May 10, 2026, 10:08 a.m. |
Created at: May 1, 2026, 12:53 a.m.