Triple
T773364
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | George "Machine Gun" Kelly |
E16331
|
entity |
| Predicate | publicEnemyStatus |
P15619
|
FINISHED |
| Object | early Public Enemy of the 1930s |
—
|
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: early Public Enemy of the 1930s | Statement: [George "Machine Gun" Kelly, publicEnemyStatus, early Public Enemy of the 1930s]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: publicEnemyStatus Context triple: [George "Machine Gun" Kelly, publicEnemyStatus, early Public Enemy of the 1930s]
-
A.
primaryEnemy
Indicates that one entity is the main or most significant adversary or opponent of another entity.
-
B.
exportStatus
Indicates the current state or outcome of an entity’s export process (e.g., pending, in progress, completed, or failed).
-
C.
enemyType
chosen
Indicates that one entity is classified as an enemy of a specified type or category in relation to another entity.
-
D.
mainCombatant
Indicates that the subject is the primary participant or leading party in a conflict, battle, or combat situation involving the object.
-
E.
targetsAsRacialEnemy
Indicates that one party identifies and treats another party as an enemy specifically on the basis of their race.
- 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_69a49369a0848190af883934cee3db4c |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a72eda6c81908205ae5a1e05cc20 |
completed | March 1, 2026, 8:53 p.m. |
| PD | Predicate disambiguation | batch_69a4a508c42c8190850a0ac7844a3ea9 |
completed | March 1, 2026, 8:43 p.m. |
Created at: March 1, 2026, 7:37 p.m.