Triple
T23294679
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Basilica of San Francesco, Ravenna |
E590130
|
entity |
| Predicate | cryptWaterSource |
P54962
|
FINISHED |
| Object | high water table |
—
|
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: high water table | Statement: [Basilica of San Francesco, Ravenna, cryptWaterSource, high water table]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cryptWaterSource Context triple: [Basilica of San Francesco, Ravenna, cryptWaterSource, high water table]
-
A.
waterSource
Indicates that one entity serves as the source or provider of water for another entity.
-
B.
waterSourceContext
chosen
Indicates the contextual relationship between a water source and the conditions, setting, or circumstances under which it is used, accessed, or relevant.
-
C.
saltSource
Indicates that one entity serves as the origin or provider of salt for another entity or process.
-
D.
sourceOfWaterSupply
Indicates that one entity serves as the origin or provider of another entity’s water supply.
-
E.
waterSourceAfter
Indicates that one water source occurs, appears, or is accessed after another in time or sequence.
- 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_69e25d1af9d88190a0b9b5e8fa608618 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f196cdce7081908ca1cf9107b87f61 |
completed | April 29, 2026, 5:27 a.m. |
| PD | Predicate disambiguation | batch_69effcf325f88190b320268c3c551abb |
completed | April 28, 2026, 12:18 a.m. |
Created at: April 17, 2026, 5:03 p.m.