Triple
T12245079
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Old Jewish Cemetery in Prague |
E291829
|
entity |
| Predicate | earliestGravesFrom |
P25897
|
FINISHED |
| Object | 1439 |
—
|
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: 1439 | Statement: [Old Jewish Cemetery in Prague, earliestGravesFrom, 1439]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: earliestGravesFrom Context triple: [Old Jewish Cemetery in Prague, earliestGravesFrom, 1439]
-
A.
earliestBurials
chosen
Indicates that the referenced burials are among the first or oldest known interments associated with a given site, group, or context.
-
B.
hasGravesFrom
Indicates that a location or site contains graves originating from or associated with a specified source place or group.
-
C.
earliestRecordedAs
Indicates the earliest known time or source at which the subject is documented or identified as having a particular status, name, or role.
-
D.
eraOfMostBurials
Indicates the historical time period during which the greatest number of burials occurred for a given site or context.
-
E.
oneOfTheOldestOn
Indicates that one entity is among the earliest or longest-existing examples within the set defined by another 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_69d6ab67950c8190be08450a06228c4b |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d91d38ee10819093ed41d2954bf4ef |
completed | April 10, 2026, 3:54 p.m. |
| PD | Predicate disambiguation | batch_69d91c46dcd88190a263db30804bff36 |
completed | April 10, 2026, 3:50 p.m. |
Created at: April 8, 2026, 9:51 p.m.