Triple
T23690969
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jajinci |
E585295
|
entity |
| Predicate | perpetratorOfMassKillings |
P68280
|
FINISHED |
| Object | Nazi German occupation forces |
—
|
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: Nazi German occupation forces | Statement: [Jajinci, perpetratorOfMassKillings, Nazi German occupation forces]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: perpetratorOfMassKillings Context triple: [Jajinci, perpetratorOfMassKillings, Nazi German occupation forces]
-
A.
massacrePerpetrators
chosen
Indicates that the subject is responsible for carrying out or participating in a massacre against the object.
-
B.
perpetratorOfKilling
Indicates that an entity is the one who carried out or caused a particular killing.
-
C.
massacreOrderedBy
Indicates that a massacre was carried out under the command, authorization, or directive of a particular person or authority.
-
D.
massacreAlsoKnownAs
Indicates that a particular massacre is known or referred to by an alternative name or names.
-
E.
notableMassKillingSite
Indicates that a place is recognized as a significant location where a mass killing or massacre occurred.
- 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_69e249037ce0819088b149608e98f685 |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b5c16af08190b2f4d126c60a7e75 |
completed | April 29, 2026, 7:39 a.m. |
| PD | Predicate disambiguation | batch_69f155d5265881908e43a9696b6a6d0f |
completed | April 29, 2026, 12:50 a.m. |
Created at: April 17, 2026, 6:52 p.m.