Triple
T13857118
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Radio France |
E333094
|
entity |
| Predicate | hasService |
P182
|
FINISHED |
| Object | Franceinfo (radio) |
E333096
|
NE 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: Franceinfo (radio) | Statement: [Radio France, hasService, Franceinfo (radio)]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Franceinfo (radio) Context triple: [Radio France, hasService, Franceinfo (radio)]
-
A.
France Info (radio)
chosen
France Info (radio) is a French public all-news radio network that provides continuous national and international news coverage.
-
B.
France Info
France Info is a French public rolling news television channel providing continuous national and international news coverage.
-
C.
Radio France
Radio France is France’s national public radio broadcaster, operating multiple nationwide stations that provide news, culture, music, and educational programming.
-
D.
Radio France headquarters
Radio France headquarters is the central broadcasting complex and main offices of the French public radio group, located in Paris.
-
E.
france.tv
france.tv is the official online streaming and catch-up TV platform of the French public broadcaster France Télévisions, offering live channels and on-demand programs.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d81c5ba13c8190839315f54768acfd |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de02dc9f488190b7181dcb7e304632 |
completed | April 14, 2026, 9:03 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7c0fb7c3c819081fc6f89aa17d6af |
completed | May 3, 2026, 9:41 p.m. |
Created at: April 9, 2026, 10:14 p.m.