Triple
T5512674
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dora di Veny |
E144602
|
entity |
| Predicate | drainageOf |
P4497
|
FINISHED |
| Object | southern side of Mont Blanc |
—
|
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: southern side of Mont Blanc | Statement: [Dora di Veny, drainageOf, southern side of Mont Blanc]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: drainageOf Context triple: [Dora di Veny, drainageOf, southern side of Mont Blanc]
-
A.
causeOfDrainage
Indicates the factor or process that leads to or is responsible for the drainage of a substance, area, or system.
-
B.
drainageType
Indicates the kind or classification of drainage associated with or applied to an entity (e.g., how water is removed or flows from it).
-
C.
drainsInto
chosen
Indicates that one entity serves as a source or conduit whose contents or flow are directed into another entity.
-
D.
drainageDivideOf
Indicates that one geographic feature functions as the drainage divide (separating water flow into different basins) for another feature or area.
-
E.
drainageResult
Indicates the outcome or effect produced by a drainage process or activity.
- 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_69c008f77ff88190b0cd50ca207295d1 |
completed | March 22, 2026, 3:21 p.m. |
| NER | Named-entity recognition | batch_69c01f581c5081909a8f6d4653edb125 |
completed | March 22, 2026, 4:56 p.m. |
| PD | Predicate disambiguation | batch_69c01b07bde08190b3933b96bdc70dd5 |
completed | March 22, 2026, 4:38 p.m. |
Created at: March 22, 2026, 3:33 p.m.