Triple

T15857567
Position Surface form Disambiguated ID Type / Status
Subject Compagnie Générale de Télégraphie Sans Fil E384499 entity
Predicate shortName P43 FINISHED
Object CSF
CSF was a major French electronics and telecommunications company known for its pioneering work in radio, radar, and defense technologies in the 20th century.
 E1179982 NE FINISHED

How this triple was built (4 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: CSF | Statement: [Compagnie Générale de Télégraphie Sans Fil, shortName, CSF]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: CSF
Context triple: [Compagnie Générale de Télégraphie Sans Fil, shortName, CSF]
  • A. CSF
    CSF is the abbreviation for the South American Football Confederation, the governing body for football in South America under CONMEBOL.
  • B. CNS
    CNS is a professional organization of neurosurgeons dedicated to advancing neurosurgical research, education, and clinical practice.
  • C. CNS
    CNS is the station code used to identify Consolação metro station in the São Paulo Metro system.
  • D. CNS
    CNS is the IATA airport code for Cairns Airport, the main international and domestic gateway to the Cairns region in Queensland, Australia.
  • E. CNSF
    CNSF is Mexico’s National Insurance and Bonding Commission, the government regulator overseeing the country’s insurance and surety sectors.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: CSF
Triple: [Compagnie Générale de Télégraphie Sans Fil, shortName, CSF]
Generated description
CSF was a major French electronics and telecommunications company known for its pioneering work in radio, radar, and defense technologies in the 20th century.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: CSF
Target entity description: CSF was a major French electronics and telecommunications company known for its pioneering work in radio, radar, and defense technologies in the 20th century.
  • A. CSF
    CSF is the abbreviation for the South American Football Confederation, the governing body for football in South America under CONMEBOL.
  • B. CNS
    CNS is a professional organization of neurosurgeons dedicated to advancing neurosurgical research, education, and clinical practice.
  • C. CNS
    CNS is the IATA airport code for Cairns Airport, the main international and domestic gateway to the Cairns region in Queensland, Australia.
  • D. CNS
    CNS is the station code used to identify Consolação metro station in the São Paulo Metro system.
  • E. CNSF
    CNSF is Mexico’s National Insurance and Bonding Commission, the government regulator overseeing the country’s insurance and surety sectors.
  • F. None of above. chosen

Provenance (5 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_69d86da422088190aac39e32e6c68429 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1555808688190882b610109d1e5f4 completed April 16, 2026, 9:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffa14c1e508190a182db216cc4e326 completed May 9, 2026, 9:04 p.m.
NEDg Description generation batch_69ffa41b33cc819096553ee33b144d36 completed May 9, 2026, 9:16 p.m.
NED2 Entity disambiguation (via description) batch_69ffa4a168108190b6edf41830aa4cd0 completed May 9, 2026, 9:18 p.m.
Created at: April 10, 2026, 4:50 a.m.