Triple
T36121122
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Trials of Henry Kissinger |
E1044742
|
entity |
| Predicate | focusesOnLegalConcept |
P113429
|
FINISHED |
| Object | crimes against humanity |
—
|
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: crimes against humanity | Statement: [The Trials of Henry Kissinger, focusesOnLegalConcept, crimes against humanity]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: focusesOnLegalConcept Context triple: [The Trials of Henry Kissinger, focusesOnLegalConcept, crimes against humanity]
-
A.
relatedLegalConcept
Indicates that one legal concept is connected or associated with another through a relevant legal relationship or context.
-
B.
legalConcept
Indicates a relationship where something is classified or treated as a concept defined and governed by law or legal theory.
-
C.
legalFeature
Indicates that something possesses a specific legal characteristic, status, or attribute relevant to laws or regulations.
-
D.
legalMatters
Indicates that one entity is involved with, concerned about, or responsible for legal issues, processes, or obligations related to another entity or context.
-
E.
mainLegalIssue
chosen
Indicates the primary legal question or dispute that is central to a case or legal matter.
- 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_69f76e356c908190abc6ca1e6a05b011 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fd389cb28c819099a77e28d25f258a |
completed | May 8, 2026, 1:13 a.m. |
| PD | Predicate disambiguation | batch_69fd3826d8048190ada79a5868d1d7f3 |
completed | May 8, 2026, 1:11 a.m. |
Created at: May 3, 2026, 4:08 p.m.