Triple
T4532581
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dublin and Monaghan bombings |
E106331
|
entity |
| Predicate | deadliestTerroristAttackIn |
P57305
|
FINISHED |
| Object | history of the Republic of Ireland |
—
|
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: history of the Republic of Ireland | Statement: [Dublin and Monaghan bombings, deadliestTerroristAttackIn, history of the Republic of Ireland]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: deadliestTerroristAttackIn Context triple: [Dublin and Monaghan bombings, deadliestTerroristAttackIn, history of the Republic of Ireland]
-
A.
countryMostVictimsFrom
Indicates the country from which the largest number of victims in a given event, situation, or context originate.
-
B.
numberOfPeopleKilledInBombing
Indicates the total count of people who were killed as a direct result of a specific bombing event.
-
C.
notableMassKillingSite
Indicates that a place is recognized as a significant location where a mass killing or massacre occurred.
-
D.
bombingName
Indicates that an entity is the name or designated title of a specific bombing event or bombing attack.
-
E.
bombingLocation
Indicates the place where a bombing event occurs or is carried out.
- 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_69bd43f3d6e08190a91824f833d51bbe |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd579f27ac8190ae9a4252109e56e1 |
completed | March 20, 2026, 2:20 p.m. |
| PD | Predicate disambiguation | batch_69bd521edd00819099dfccaa65dddd61 |
completed | March 20, 2026, 1:56 p.m. |
| PDg | Predicate description generation | batch_69bd56b3e4c88190a7ade3d0ed0ab606 |
completed | March 20, 2026, 2:16 p.m. |
Created at: March 20, 2026, 1:03 p.m.