Triple

T12564134
Position Surface form Disambiguated ID Type / Status
Subject Havas E295423 entity
Predicate hasSubsidiary P254 FINISHED
Object BETC
BETC is a prominent French advertising and communications agency known for its creative campaigns and as a key part of the Havas group.
E991303 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: BETC | Statement: [Havas, hasSubsidiary, BETC]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: BETC
Context triple: [Havas, hasSubsidiary, BETC]
  • A. BES
    BES is the international vehicle registration code used for the Caribbean Netherlands islands of Bonaire, Sint Eustatius, and Saba.
  • B. BEK
    BEK is the IATA airport code for Bareilly Airport, a domestic airport serving the city of Bareilly in Uttar Pradesh, India.
  • C. BEP
    BEP is a United States government agency responsible for designing and producing paper currency and other secure documents.
  • D. BTL
    BTL is the IATA airport code for W. K. Kellogg Airport, a public airport serving the Battle Creek, Michigan area.
  • E. BEAS
    BEAS was the stock ticker symbol for BEA Systems, a software company best known for its enterprise middleware and WebLogic application server before being acquired by Oracle.
  • 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: BETC
Triple: [Havas, hasSubsidiary, BETC]
Generated description
BETC is a prominent French advertising and communications agency known for its creative campaigns and as a key part of the Havas group.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: BETC
Target entity description: BETC is a prominent French advertising and communications agency known for its creative campaigns and as a key part of the Havas group.
  • A. BES
    BES is the international vehicle registration code used for the Caribbean Netherlands islands of Bonaire, Sint Eustatius, and Saba.
  • B. BEK
    BEK is the IATA airport code for Bareilly Airport, a domestic airport serving the city of Bareilly in Uttar Pradesh, India.
  • C. BEP
    BEP is a United States government agency responsible for designing and producing paper currency and other secure documents.
  • D. BTL
    BTL is the IATA airport code for W. K. Kellogg Airport, a public airport serving the Battle Creek, Michigan area.
  • E. BEAS
    BEAS was the stock ticker symbol for BEA Systems, a software company best known for its enterprise middleware and WebLogic application server before being acquired by Oracle.
  • 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_69d6ad9cac2c81908e8a7bed82d1e21d completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d95494ae1c81908b9ee14b8ef92a65 completed April 10, 2026, 7:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6558da7e0819086860bfaf394e2d8 completed May 2, 2026, 7:50 p.m.
NEDg Description generation batch_69f65a0f1b2881908a7cb21c9de1a5c2 completed May 2, 2026, 8:09 p.m.
NED2 Entity disambiguation (via description) batch_69f65ad4424c8190933759cca5d73c22 completed May 2, 2026, 8:13 p.m.
Created at: April 8, 2026, 11:49 p.m.