Triple
T16033889
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prekaz massacre |
E388916
|
entity |
| Predicate | militantDeaths |
P1785
|
FINISHED |
| Object | multiple KLA fighters |
—
|
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: multiple KLA fighters | Statement: [Prekaz massacre, militantDeaths, multiple KLA fighters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: militantDeaths Context triple: [Prekaz massacre, militantDeaths, multiple KLA fighters]
-
A.
militantCasualtiesEstimate
Indicates an estimated number of militants who have been killed, wounded, or otherwise rendered casualties in a conflict or operation.
-
B.
conflictOfDeath
Indicates a relationship where a death occurs as a result of, or in the context of, an armed conflict or war.
-
C.
martyredUnder
Indicates that an entity was killed or executed as a martyr during the rule, authority, or actions of another entity.
-
D.
deathToll
chosen
Indicates the number of deaths resulting from a particular event, situation, or cause.
-
E.
governmentCasualties
Indicates that members of a government (such as officials, employees, or security forces) were killed, injured, or otherwise became casualties in an event or conflict.
- 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_69d86dada3808190825d5f80d72fbe88 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e1ff63edb0819092cbb671967bbdcd |
completed | April 17, 2026, 9:37 a.m. |
| PD | Predicate disambiguation | batch_69e1826f34c081908005bb736f1c485d |
completed | April 17, 2026, 12:44 a.m. |
Created at: April 10, 2026, 4:56 a.m.