Triple
T16720509
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Croke Park shootings |
E406334
|
entity |
| Predicate | immediateContext |
P124369
|
FINISHED |
| Object | reprisal for assassinations of British intelligence officers in Dublin |
—
|
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: reprisal for assassinations of British intelligence officers in Dublin | Statement: [Croke Park shootings, immediateContext, reprisal for assassinations of British intelligence officers in Dublin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: immediateContext Context triple: [Croke Park shootings, immediateContext, reprisal for assassinations of British intelligence officers in Dublin]
-
A.
bindingContext
Indicates the contextual or situational conditions under which one entity is bound or associated to another (e.g., scope, environment, or circumstances of the binding).
-
B.
unitContext
Indicates the contextual framework or setting (such as scope, conditions, or environment) within which a particular unit, instance, or occurrence is defined or interpreted.
-
C.
operatorContext
Indicates the situational or environmental conditions under which an operator performs an action or maintains a relationship with another entity.
-
D.
contextName
Indicates the specific contextual label or identifier under which an entity, event, or relation is defined or interpreted.
-
E.
recaptureContext
Indicates that a previously established context or situation is being regained or restored after it was lost, interrupted, or diminished.
- F. None of above. chosen
Provenance (4 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_69d8838f242881908abd8bc138795886 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e3874270748190ad7c3b3531293b60 |
completed | April 18, 2026, 1:29 p.m. |
| PD | Predicate disambiguation | batch_69e319c379f88190ac0adf812486f598 |
completed | April 18, 2026, 5:42 a.m. |
| PDg | Predicate description generation | batch_69e326b9e84881909a9166e65bd850d6 |
completed | April 18, 2026, 6:37 a.m. |
Created at: April 10, 2026, 5:20 a.m.