Triple
T25945564
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dutchbat |
E653829
|
entity |
| Predicate | relatedMassKilling |
P89142
|
FINISHED |
| Object | murder of more than 8,000 Bosniak men and boys |
—
|
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: murder of more than 8,000 Bosniak men and boys | Statement: [Dutchbat, relatedMassKilling, murder of more than 8,000 Bosniak men and boys]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relatedMassKilling Context triple: [Dutchbat, relatedMassKilling, murder of more than 8,000 Bosniak men and boys]
-
A.
relatedMassAtrocityContext
Indicates that an entity is connected to, associated with, or occurs within the broader circumstances or environment of a mass atrocity event.
-
B.
massacreOccurred
chosen
Indicates that a large-scale, deliberate killing of multiple individuals took place in a specific event or context.
-
C.
massacreAlsoKnownAs
Indicates that a particular massacre is known or referred to by an alternative name or names.
-
D.
timeOfMassViolence
Indicates the specific time at which an act or event of mass violence occurred.
-
E.
massacreOccurredIn
Indicates that a massacre took place within the specified location or area.
- 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_69e7ab40ac788190a771bc499eb1ae5f |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69fd82ed2a4c81908bd7797fbd2e3d08 |
completed | May 8, 2026, 6:30 a.m. |
| PD | Predicate disambiguation | batch_69fd814cc10481908e4f8123d35a5d0c |
completed | May 8, 2026, 6:23 a.m. |
Created at: April 22, 2026, 8:43 a.m.