Triple
T261845
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | War in Afghanistan (2001–2021) |
E5556
|
entity |
| Predicate | civilianDeathsEstimate |
P700
|
FINISHED |
| Object | over 40,000 |
—
|
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: over 40,000 | Statement: [War in Afghanistan (2001–2021), civilianDeathsEstimate, over 40,000]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: civilianDeathsEstimate Context triple: [War in Afghanistan (2001–2021), civilianDeathsEstimate, over 40,000]
-
A.
militaryCasualtiesEstimate
Indicates an estimated number of people killed, wounded, or missing as a result of military conflict or operations.
-
B.
casualtiesEstimate
Indicates an estimated number of people killed, injured, or otherwise harmed as a result of an event or incident.
-
C.
deathTollEstimate
chosen
Indicates an estimated number of deaths attributed to a particular event, cause, or period.
-
D.
deathToll
Indicates the number of deaths resulting from a particular event, situation, or cause.
-
E.
buildingsDestroyed
Indicates that one or more buildings have been damaged to the point of destruction as a result of some event or action.
- 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_69a2580a64ac8190ad76e34bb0715b5e |
completed | Feb. 28, 2026, 2:50 a.m. |
| NER | Named-entity recognition | batch_69a25e2aba74819093eddd8d820260c0 |
completed | Feb. 28, 2026, 3:16 a.m. |
| PD | Predicate disambiguation | batch_69a25b6c968c819094fc903a3a377e15 |
completed | Feb. 28, 2026, 3:05 a.m. |
Created at: Feb. 28, 2026, 2:55 a.m.