Triple
T6357327
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1983 United States Embassy bombing in Beirut |
E143023
|
entity |
| Predicate | fatalitiesLocals |
P1785
|
FINISHED |
| Object | dozens of Lebanese |
—
|
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: dozens of Lebanese | Statement: [1983 United States Embassy bombing in Beirut, fatalitiesLocals, dozens of Lebanese]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fatalitiesLocals Context triple: [1983 United States Embassy bombing in Beirut, fatalitiesLocals, dozens of Lebanese]
-
A.
fatalitiesCategory
Indicates the classification of deaths associated with an event, incident, or condition into a specific category or severity level.
-
B.
nativeCasualties
Indicates that native or indigenous people suffered deaths or injuries as a result of a particular event, action, or conflict.
-
C.
mainVictims
Indicates that the related entities are the primary or principal targets harmed or affected by an action, event, or perpetrator.
-
D.
hadNoFatalities
Indicates that the referenced event, incident, or situation resulted in zero deaths.
-
E.
deathToll
chosen
Indicates the number of deaths resulting from a particular event, situation, or cause.
- 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_69c008d7a9c4819098d647ec47776917 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c067f37d0881909289bafb09e29298 |
completed | March 22, 2026, 10:06 p.m. |
| PD | Predicate disambiguation | batch_69c060ec091c8190912aac44e1b8b1c9 |
completed | March 22, 2026, 9:36 p.m. |
Created at: March 22, 2026, 4:32 p.m.