Triple
T26211871
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prosecutor v. Radovan Karadžić |
E655510
|
entity |
| Predicate | modeOfLiability |
P160530
|
FINISHED |
| Object | command responsibility |
—
|
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: command responsibility | Statement: [Prosecutor v. Radovan Karadžić, modeOfLiability, command responsibility]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: modeOfLiability Context triple: [Prosecutor v. Radovan Karadžić, modeOfLiability, command responsibility]
-
A.
modeOfLiability
chosen
Indicates the specific legal basis or manner in which an entity is held responsible for an act or outcome.
-
B.
liabilityType
Indicates the specific category or nature of liability associated with an entity, obligation, or financial exposure.
-
C.
establishesLiabilityFor
Indicates that one party is held legally responsible or accountable for a particular act, omission, or outcome.
-
D.
carrierLiabilityType
Indicates the specific type or category of legal or contractual liability that a carrier assumes in relation to the goods or services it transports or provides.
-
E.
recallLiability
Indicates a relationship where an entity bears legal or financial responsibility for initiating or managing a product recall.
- 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_69ee5b49adb4819086545280d4ef6337 |
completed | April 26, 2026, 6:36 p.m. |
| NER | Named-entity recognition | batch_69f60d1804548190ab0bba3376f28269 |
completed | May 2, 2026, 2:41 p.m. |
| PD | Predicate disambiguation | batch_69f60b874cc88190a487230abb69efea |
completed | May 2, 2026, 2:34 p.m. |
Created at: April 26, 2026, 8:52 p.m.