Triple
T5194764
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fontaine-de-Vaucluse |
E117242
|
entity |
| Predicate | springRank |
P62378
|
FINISHED |
| Object | among the largest springs in the world by flow |
—
|
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: among the largest springs in the world by flow | Statement: [Fontaine-de-Vaucluse, springRank, among the largest springs in the world by flow]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: springRank Context triple: [Fontaine-de-Vaucluse, springRank, among the largest springs in the world by flow]
-
A.
SSRank
Indicates a ranking relationship that orders entities based on their social status, standing, or relative importance within a specified context.
-
B.
peakRanking
Indicates the highest position or rank an entity has ever achieved within a specified ranking system or context.
-
C.
selectionRankingEndPoint
Indicates the position or boundary in an ordered list at which a selection or ranking process concludes.
-
D.
rankingScope
Indicates the context or domain within which a ranking is defined, interpreted, or applied.
-
E.
usesRank
Indicates that one entity applies or relies on a ranking or ordered level system associated with another entity.
- 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_69bd4462ed04819084fcb01eb9d2fa74 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd7adb034c819086bf8a85fbf158f4 |
completed | March 20, 2026, 4:50 p.m. |
| PD | Predicate disambiguation | batch_69bd77b9a67c8190819612257ea746b4 |
completed | March 20, 2026, 4:37 p.m. |
| PDg | Predicate description generation | batch_69bd7ad9bdd88190ae8aa6f4aba695a7 |
completed | March 20, 2026, 4:50 p.m. |
Created at: March 20, 2026, 1:46 p.m.