Triple
T5098491
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brunswick Manifesto |
E114924
|
entity |
| Predicate | threatenedAction |
P1358
|
FINISHED |
| Object | severe reprisals against Paris if the royal family were harmed |
—
|
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: severe reprisals against Paris if the royal family were harmed | Statement: [Brunswick Manifesto, threatenedAction, severe reprisals against Paris if the royal family were harmed]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: threatenedAction Context triple: [Brunswick Manifesto, threatenedAction, severe reprisals against Paris if the royal family were harmed]
-
A.
threatenedBy
Indicates that one entity poses a danger or potential harm to another entity.
-
B.
threatToHumans
Indicates that the subject poses or represents a potential danger, harm, or risk to humans.
-
C.
threatenedToKill
Indicates that one entity has made a threat or expressed an intention to kill another entity.
-
D.
threat
chosen
Indicates a relationship where one entity expresses or poses potential harm, danger, or negative consequences toward another entity.
-
E.
threatType
Indicates the specific category or nature of a threat that one entity poses or represents in relation to another.
- 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_69bd443fc49c819089629c00e311310c |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd7567d21081909227ed8f08b74c71 |
completed | March 20, 2026, 4:27 p.m. |
| PD | Predicate disambiguation | batch_69bd715e06808190931934dc9930f997 |
completed | March 20, 2026, 4:10 p.m. |
Created at: March 20, 2026, 1:40 p.m.