Triple
T34952052
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jan Lucemburský |
E1008025
|
entity |
| Predicate | slepota |
P181888
|
FINISHED |
| Object | oslepl na obě oči před bitvou u Kresčaku |
—
|
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: oslepl na obě oči před bitvou u Kresčaku | Statement: [Jan Lucemburský, slepota, oslepl na obě oči před bitvou u Kresčaku]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: slepota Context triple: [Jan Lucemburský, slepota, oslepl na obě oči před bitvou u Kresčaku]
-
A.
sleepCurse
Indicates a condition where one entity has magically imposed or is affected by a curse that causes unnatural or enforced sleep.
-
B.
fallsAsleepIn
Indicates that one entity begins sleeping while located within or inside another entity or context.
-
C.
sleepDisorderContext
Indicates that the relationship or action occurs within the context of a sleep disorder, such as being caused by, associated with, or relevant to that disorder.
-
D.
slows
Indicates that one entity causes another entity’s speed, rate, or progress to decrease.
-
E.
restOn
Indicates that one entity is physically supported by and in contact with the surface of another entity, typically in a stable, stationary position.
- F. None of above. chosen
Provenance (4 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_69f76dc5d4308190b77553ee07b1ede6 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f782cf61948190b98185d961609554 |
completed | May 3, 2026, 5:15 p.m. |
| PD | Predicate disambiguation | batch_69f781020cc4819088c40cb8589504e4 |
completed | May 3, 2026, 5:08 p.m. |
| PDg | Predicate description generation | batch_69f782c848fc8190baea8c845ca9079f |
completed | May 3, 2026, 5:15 p.m. |
Created at: May 3, 2026, 4 p.m.