Triple
T22703928
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | State Property 2 |
E561394
|
entity |
| Predicate | portraysIllegalActivity |
P110358
|
FINISHED |
| Object | drug trafficking |
—
|
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: drug trafficking | Statement: [State Property 2, portraysIllegalActivity, drug trafficking]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: portraysIllegalActivity Context triple: [State Property 2, portraysIllegalActivity, drug trafficking]
-
A.
illegalActivityAssociatedWith
Indicates that there is a connection between an entity and an unlawful or criminal activity.
-
B.
portraysActivity
chosen
Indicates that one entity visually or narratively represents another entity engaged in a particular activity.
-
C.
reservedLegalActivity
Indicates that a particular legal action, service, or function is restricted to authorized or qualified parties and may not be performed freely by others.
-
D.
reportsCertainActsTo
Indicates that one entity informs an authority or designated party about specific actions or incidents carried out by another entity.
-
E.
portraysInvestigationOf
Indicates that one entity depicts, represents, or illustrates the process, details, or conduct of an investigation concerning another entity.
- 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_69e2454e615481909c177440be559d2c |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f178cca1e48190bbe7910f13692803 |
completed | April 29, 2026, 3:19 a.m. |
| PD | Predicate disambiguation | batch_69ee62bd657c81909f7b01245b080a5f |
completed | April 26, 2026, 7:08 p.m. |
Created at: April 17, 2026, 3:16 p.m.