Triple
T19702813
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tunisian National Dialogue Quartet |
E473136
|
entity |
| Predicate | helpedPrevent |
P33311
|
FINISHED |
| Object | escalation of political violence in Tunisia |
—
|
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: escalation of political violence in Tunisia | Statement: [Tunisian National Dialogue Quartet, helpedPrevent, escalation of political violence in Tunisia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: helpedPrevent Context triple: [Tunisian National Dialogue Quartet, helpedPrevent, escalation of political violence in Tunisia]
-
A.
prevented
Indicates that one entity stopped, hindered, or made it impossible for another entity or event to occur or proceed.
-
B.
worksToPrevent
chosen
Indicates an entity actively takes measures or engages in actions to stop, reduce, or avoid the occurrence or impact of another entity or condition.
-
C.
helpedCause
Indicates that one entity contributed to bringing about, enabling, or facilitating an outcome or event involving another entity.
-
D.
helpedEscape
Indicates that one entity assisted another in getting away from confinement, danger, or pursuit.
-
E.
helpedSecure
Indicates that one entity contributed to obtaining, protecting, or ensuring the safety or stability of another entity or outcome.
- 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_69d8e516dd048190a0b6c93ea3e71f58 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e642b758348190b0cf58d6b2f13e7f |
completed | April 20, 2026, 3:13 p.m. |
| PD | Predicate disambiguation | batch_69e530438c60819082364c7be3eef6f0 |
completed | April 19, 2026, 7:42 p.m. |
Created at: April 10, 2026, 1:46 p.m.