Triple
T5934473
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vivendi |
E132009
|
entity |
| Predicate | subsidiary |
P258
|
FINISHED |
| Object | Havas Group |
E295423
|
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: Havas Group | Statement: [Vivendi, subsidiary, Havas Group]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Havas Group Context triple: [Vivendi, subsidiary, Havas Group]
-
A.
Havas
chosen
Havas is a major global advertising and communications group headquartered in France, known for its extensive network of creative, media, and marketing agencies.
-
B.
Publicis Groupe
Publicis Groupe is a major French multinational advertising and communications company and one of the world’s largest marketing services groups.
-
C.
WPP plc
WPP plc is a British multinational advertising and public relations conglomerate and one of the world’s largest communications groups.
-
D.
Omnicom Group
Omnicom Group is a global marketing and communications holding company that owns numerous leading advertising, media, and public relations agencies worldwide.
-
E.
Wunderman
Wunderman is a global marketing and advertising agency known for its data-driven, digital-first campaigns and customer relationship management services.
- 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_69c0085c55dc8190aa90e242c956e2fa |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c038a0c4e481908170d615330edb1a |
completed | March 22, 2026, 6:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c0e3b68a1c81908a219ffee8300e02 |
completed | March 23, 2026, 6:54 a.m. |
Created at: March 22, 2026, 4 p.m.