Triple
T26920141
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bill Marks |
E677621
|
entity |
| Predicate | receivesThreatsVia |
P147428
|
FINISHED |
| Object | encrypted text messages |
—
|
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: encrypted text messages | Statement: [Bill Marks, receivesThreatsVia, encrypted text messages]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: receivesThreatsVia Context triple: [Bill Marks, receivesThreatsVia, encrypted text messages]
-
A.
hasThreats
Indicates that one entity poses or is associated with potential danger, harm, or adverse consequences toward another entity.
-
B.
recognizesThreat
Indicates that an entity identifies or acknowledges another entity or situation as a potential danger or source of harm.
-
C.
threatsFaced
chosen
Indicates that an entity is exposed to or experiences specific dangers, risks, or harmful conditions.
-
D.
targetsThreat
Indicates that one entity is directing an action or focus specifically toward a perceived threat.
-
E.
laterThreat
Indicates that one entity poses a threat to another at a time subsequent to some referenced or initial point.
- 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_69eee9bdebc48190ba90a12a63e09c73 |
completed | April 27, 2026, 4:44 a.m. |
| NER | Named-entity recognition | batch_69f65aa07c048190a5df30d53d8f0cf5 |
completed | May 2, 2026, 8:12 p.m. |
| PD | Predicate disambiguation | batch_69f659cc571c819097e51e531961d812 |
completed | May 2, 2026, 8:08 p.m. |
Created at: April 27, 2026, 6:06 a.m.