Triple
T30104971
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oiseaux |
E765106
|
entity |
| Predicate | hasCountryOfLocalization |
P190537
|
FINISHED |
| Object | France |
—
|
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: France | Statement: [Oiseaux, hasCountryOfLocalization, France]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCountryOfLocalization Context triple: [Oiseaux, hasCountryOfLocalization, France]
-
A.
nationalityInLocalization
Indicates that a specific nationality is associated with, or expressed within, a particular localized context (such as language, region, or cultural setting).
-
B.
hasLanguageInCountry
Indicates that a particular language is used or recognized within a specified country.
-
C.
localizedIn
chosen
Indicates that one entity is situated, confined, or occurs within a specific region, area, or context defined by another entity.
-
D.
languageOfLocalization
Indicates the language into which something (such as software, content, or an interface) has been localized for use or display.
-
E.
localizationBy
Indicates a relationship where one entity determines, specifies, or constrains the spatial or contextual location of another entity.
- 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_69f22474e4288190b5f895fe3974aa92 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_6a00d08e8fac8190b59359134e6e1c03 |
completed | May 10, 2026, 6:38 p.m. |
| PD | Predicate disambiguation | batch_6a00d0127c088190a6f5b360450af113 |
completed | May 10, 2026, 6:36 p.m. |
Created at: April 29, 2026, 7:09 p.m.