Triple

T13857116
Position Surface form Disambiguated ID Type / Status
Subject Radio France E333094 entity
Predicate hasService P182 FINISHED
Object FIP E980632 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: FIP | Statement: [Radio France, hasService, FIP]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: FIP
Context triple: [Radio France, hasService, FIP]
  • A. FIP chosen
    FIP is a French public radio station known for its eclectic, commercial-free music programming and relaxed, continuous broadcast style.
  • B. FIPV
    FIPV is the international federation responsible for overseeing and regulating the sport of Basque pelota worldwide.
  • C. FIF
    FIF is the abbreviation for the Fife Flyers, a professional ice hockey team based in Kirkcaldy, Scotland.
  • D. FVR
    FVR is the commonly used initials and nickname of Fidel V. Ramos, the former President of the Philippines.
  • E. FIPC
    FIPC is a key policymaking body within the Bank of Thailand responsible for formulating and overseeing policies related to financial institutions and the stability of the financial system.
  • 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.