Triple
T37473507
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ZCK w Krakowie |
E931214
|
entity |
| Predicate | operatesCemeteryType |
P2742
|
FINISHED |
| Object | communal cemetery |
—
|
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: communal cemetery | Statement: [ZCK w Krakowie, operatesCemeteryType, communal cemetery]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: operatesCemeteryType Context triple: [ZCK w Krakowie, operatesCemeteryType, communal cemetery]
-
A.
cemeteryType
chosen
Indicates the specific kind or classification of a cemetery associated with an entity.
-
B.
hasCemeteryType
Indicates that a cemetery is classified as belonging to a specific type or category of cemetery.
-
C.
hasCemetery
Indicates that one entity possesses, contains, or includes a cemetery associated with it.
-
D.
cemeteryCapacitySupported
Indicates that an entity provides or supports the necessary capacity (such as space or resources) for a cemetery to operate or accommodate burials.
-
E.
mortuaryType
Indicates the specific kind or category of mortuary facility or service associated with an entity.
- 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_69f76ec2af148190897d101070d7f415 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a02fc3890a881908b69b0f2d7cc1ce1 |
completed | May 12, 2026, 10:08 a.m. |
| PD | Predicate disambiguation | batch_6a02fb98438c8190938896c00216b9ec |
completed | May 12, 2026, 10:06 a.m. |
Created at: May 3, 2026, 4:17 p.m.