Triple

T13857218
Position Surface form Disambiguated ID Type / Status
Subject France Info (radio) E333096 entity
Predicate partOf P40 FINISHED
Object France Info (brand) 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: France Info (brand) | Statement: [France Info (radio), partOf, France Info (brand)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: France Info (brand)
Context triple: [France Info (radio), partOf, France Info (brand)]
  • 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. Orange France
    Orange France is a major French telecommunications operator providing mobile, internet, and other communication services across France.
  • D. France 3
    France 3 is a French public television channel known for its regional programming and news coverage as part of the France Télévisions group.
  • E. HuffPost France
    HuffPost France is the French edition of the online news and opinion website HuffPost, offering digital journalism, blogs, and commentary on national and international current affairs.
  • 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.