Triple
T36608166
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Blackwater USA |
E903092
|
entity |
| Predicate | numberOfCivilianDeathsAtNisourSquare |
—
|
GENERATED |
| Object | 17 |
—
|
UNRECOGNIZED GENERATED |
How this triple was built (1 step)
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.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numberOfCivilianDeathsAtNisourSquare Context triple: [Blackwater USA, numberOfCivilianDeathsAtNisourSquare, 17]
-
A.
numberOfCiviliansInjured
Indicates the count of civilian individuals who were injured as a result of a specific event or action.
-
B.
casualtiesCiviliansKilled
chosen
Indicates that the relationship records the number of civilian deaths resulting from a specific event or action.
-
C.
deathInTerroristAttack
Indicates that an entity died as a direct result of a terrorist attack.
-
D.
numberOfPeopleInjuredInBombings
Indicates the count of individuals who were injured as a result of bombing incidents.
-
E.
numberOfPeopleKilledInBombing
Indicates the total count of people who were killed as a direct result of a specific bombing event.
- F. None of above.
Provenance (1 batch)
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_69f76e66b7b88190848f7a3e1188915f |
completed | May 3, 2026, 3:48 p.m. |
Created at: May 3, 2026, 4:11 p.m.