Triple
T13058122
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Amnesty Committee |
E327629
|
entity |
| Predicate | scopeOfCrimes |
P7957
|
FINISHED |
| Object | killings |
—
|
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: killings | Statement: [Amnesty Committee, scopeOfCrimes, killings]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: scopeOfCrimes Context triple: [Amnesty Committee, scopeOfCrimes, killings]
-
A.
crimeType
chosen
Indicates the specific category or nature of the crime associated with an event or entity.
-
B.
criminalType
Indicates the specific category or classification of crime associated with a criminal act or offender.
-
C.
recognitionOfCrimes
Indicates the formal acknowledgment or identification that certain actions or events constitute crimes under a legal or normative framework.
-
D.
includesCrimesAgainstSociety
Indicates that the referenced entity involves, encompasses, or is associated with offenses classified as crimes against society (such as public order, moral, or regulatory violations).
-
E.
committedCrime
Indicates that an entity has carried out or been responsible for a criminal act or offense.
- 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_69d8076e64308190904fb5c93517c901 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69d980e7ee548190b4b18bdb1357c359 |
completed | April 10, 2026, 10:59 p.m. |
| PD | Predicate disambiguation | batch_69d9803d46688190bac6b7d208f08d01 |
completed | April 10, 2026, 10:57 p.m. |
Created at: April 9, 2026, 8:58 p.m.