Triple
T9691108
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Exhibition House for Crimes of War and Aggression |
E234536
|
entity |
| Predicate | documentedTopic |
P26448
|
FINISHED |
| Object | war crimes |
—
|
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: war crimes | Statement: [Exhibition House for Crimes of War and Aggression, documentedTopic, war crimes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: documentedTopic Context triple: [Exhibition House for Crimes of War and Aggression, documentedTopic, war crimes]
-
A.
documentedThrough
Indicates that something is recorded, evidenced, or made known by means of a specific document or documentation process.
-
B.
documentedUsing
Indicates that something is recorded, described, or specified by means of a particular document, tool, or documentation method.
-
C.
governedTopic
Indicates that a governing entity exercises authority, control, or regulatory oversight over a particular topic, issue, or domain.
-
D.
featuresTopic
chosen
Indicates that something (such as a work, event, or item) prominently includes, focuses on, or is organized around a particular topic.
-
E.
documentedBy
Indicates that something is recorded, described, or evidenced in a specific document or set of documents.
- 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_69ca84ca73208190957a900c8543bdcc |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cd9d0422e88190a234ba74eb0dad25 |
completed | April 1, 2026, 10:32 p.m. |
| PD | Predicate disambiguation | batch_69ccd5b840f081909f66bf0b66d17d9b |
completed | April 1, 2026, 8:22 a.m. |
Created at: March 30, 2026, 8:17 p.m.