Triple
T20951990
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | R v McIlkenny and others |
E516000
|
entity |
| Predicate | numberOfPeopleKilledInBombings |
P5123
|
FINISHED |
| Object | 21 |
—
|
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: 21 | Statement: [R v McIlkenny and others, numberOfPeopleKilledInBombings, 21]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numberOfPeopleKilledInBombings Context triple: [R v McIlkenny and others, numberOfPeopleKilledInBombings, 21]
-
A.
numberOfPeopleKilledInBombing
chosen
Indicates the total count of people who were killed as a direct result of a specific bombing event.
-
B.
numberOfSuicideBombers
Indicates the quantity of individuals who carry out or are intended to carry out suicide bombing attacks.
-
C.
deadliestTerroristAttackIn
Indicates that a terrorist attack is the most lethal one that has occurred within a specified place or region.
-
D.
resultOfBombing
Indicates that something exists or occurs as a consequence or outcome of a bombing event.
-
E.
deathInTerroristAttack
Indicates that an entity died as a direct result of a terrorist attack.
- 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_69e0b4fcd678819087a304291f14330a |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6fade4e2c81908ab2619d74fcc5a7 |
completed | April 21, 2026, 4:19 a.m. |
| PD | Predicate disambiguation | batch_69e5c9b1bae48190a845165fed1b005e |
completed | April 20, 2026, 6:37 a.m. |
Created at: April 16, 2026, 1:27 p.m.