Triple
T15170205
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aquitanian culture |
E362465
|
entity |
| Predicate | hasRootsIn |
P34787
|
FINISHED |
| Object | pre-Roman traditions |
—
|
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: pre-Roman traditions | Statement: [Aquitanian culture, hasRootsIn, pre-Roman traditions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRootsIn Context triple: [Aquitanian culture, hasRootsIn, pre-Roman traditions]
-
A.
isRootOf
Indicates that one entity is the root or origin point from which another entity directly or indirectly descends or is derived.
-
B.
hasRootSystem
Indicates that one entity possesses or is characterized by a particular type of root system.
-
C.
containsRootsOfUnity
Indicates that one mathematical object includes all elements that are roots of unity within a specified context or structure.
-
D.
hasAncestralRoots
chosen
Indicates that one entity originates from, descends from, or is historically rooted in another entity or place.
-
E.
arePolynomialsIn
Indicates that the specified expressions are polynomials in the given variable(s) or over the given ring/field.
- 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_69d85a087b7c81908baa94a53dac8d68 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e0064ec56481909f11fa6e5686f076 |
completed | April 15, 2026, 9:42 p.m. |
| PD | Predicate disambiguation | batch_69deb9779acc81908ed2dad382c42dca |
completed | April 14, 2026, 10:02 p.m. |
Created at: April 10, 2026, 3:08 a.m.