Triple
T27638285
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Europe à plusieurs vitesses |
E696521
|
entity |
| Predicate | traductionApprox |
P15005
|
FINISHED |
| Object | multi-speed Europe |
—
|
NE NERFINISHED |
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: multi-speed Europe | Statement: [Europe à plusieurs vitesses, traductionApprox, multi-speed Europe]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: traductionApprox Context triple: [Europe à plusieurs vitesses, traductionApprox, multi-speed Europe]
-
A.
translationApproximate
chosen
Indicates that one entity is an inexact or approximate translation of another, preserving general meaning but not precise wording or full detail.
-
B.
literalMeaningApproximation
Indicates that one entity expresses an approximate or rough literal meaning of another entity, rather than an exact or fully precise interpretation.
-
C.
translatedIn
Indicates that a work, text, or content has been rendered from its original language into another specified language or linguistic form.
-
D.
translationProperty
Indicates a relationship where one entity serves as a translated counterpart or translation-specific attribute of another entity.
-
E.
translationOn
Indicates that one entity is a translation of another entity, typically expressing the same content in a different language or linguistic form.
- 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_69ef5909f3848190805f35b76833e722 |
completed | April 27, 2026, 12:39 p.m. |
| NER | Named-entity recognition | batch_69f6318e4c9c8190960df19eed7546fa |
completed | May 2, 2026, 5:17 p.m. |
| PD | Predicate disambiguation | batch_69f62c1921008190a62675a31f66a875 |
completed | May 2, 2026, 4:53 p.m. |
Created at: April 27, 2026, 2:25 p.m.