Triple
T23405075
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jilava Massacre |
E559612
|
entity |
| Predicate | location |
P40
|
FINISHED |
| Object | Jilava |
—
|
NE NERFINISHED |
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: Jilava | Statement: [Jilava Massacre, location, Jilava]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jilava Context triple: [Jilava Massacre, location, Jilava]
-
A.
Jilava
chosen
Jilava is a locality in Romania best known for its historic prison and fortress, which were used for political detentions and executions, especially during the 20th century.
-
B.
Lučina
Lučina is a river in the Moravian-Silesian Region of the Czech Republic that flows through the city of Ostrava.
-
C.
Jizerka
Jizerka is a small mountain settlement and popular tourist destination in the Jizera Mountains of the Czech Republic, known for its dark skies, peat bogs, and well-preserved natural landscape.
-
D.
Božava
Božava is a small coastal village and tourist resort on the island of Dugi Otok in Croatia, known for its picturesque harbor and nearby beaches.
-
E.
Bílina
Bílina is a river in the Czech Republic that flows through the Ústí nad Labem Region and is known for passing through several industrial and mining areas.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e24549610c8190a069d6411ce5f661 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1a4e27db88190b37375b38073291c |
completed | April 29, 2026, 6:27 a.m. |
Created at: April 17, 2026, 5:38 p.m.