Triple
T32910842
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Baradla Cave |
E841871
|
entity |
| Predicate | hasLengthInHungary |
P89624
|
FINISHED |
| Object | approximately 18 kilometers |
—
|
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: approximately 18 kilometers | Statement: [Baradla Cave, hasLengthInHungary, approximately 18 kilometers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLengthInHungary Context triple: [Baradla Cave, hasLengthInHungary, approximately 18 kilometers]
-
A.
lengthInHungary
chosen
Indicates that something has a specified length measured within the context or territory of Hungary.
-
B.
nameInHungarian
Indicates that one entity is the Hungarian-language name or designation of another entity.
-
C.
hasGivenNameFormInHungarian
Indicates that an entity’s given name is expressed in its specific Hungarian linguistic form.
-
D.
lengthInCzechRepublic
Indicates the extent or measurement of something specifically within the geographic boundaries of the Czech Republic.
-
E.
lengthInAustria
Indicates that a specified length measurement is taken within, or applies specifically to, the context of Austria.
- 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_69f34946a5208190bbd79f0fec4323bd |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69fd7fdafbe881908a31fcb407af2c34 |
completed | May 8, 2026, 6:16 a.m. |
| PD | Predicate disambiguation | batch_69fd7ef0ea908190b5d83f71565bdb1c |
completed | May 8, 2026, 6:13 a.m. |
Created at: May 1, 2026, 1:19 a.m.