Triple
T22504012
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Publicis Groupe |
E556342
|
entity |
| Predicate | servesClientsWorldwide |
P28884
|
FINISHED |
| Object | true |
—
|
LITERAL 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: true | Statement: [Publicis Groupe, servesClientsWorldwide, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: servesClientsWorldwide Context triple: [Publicis Groupe, servesClientsWorldwide, true]
-
A.
servesCommunitiesWorldwide
Indicates that the subject provides services or support to communities across multiple countries or regions around the world.
-
B.
usedWorldwide
Indicates that something is utilized or applied across many countries or regions around the world.
-
C.
operatesInternationally
chosen
Indicates that the entity conducts activities or business across national borders in multiple countries.
-
D.
salesWorldwide
Indicates a relationship where an entity’s sales figures or activities are measured, reported, or occur across multiple countries or global markets.
-
E.
destinationCountryServed
Indicates that a given entity (such as a service, route, or provider) serves or operates to a specified destination country.
- F. None of above.
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_69e11e555edc81909ca803587dafd747 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15d5ac5808190a66f9111c350f4dc |
completed | April 29, 2026, 1:22 a.m. |
| PD | Predicate disambiguation | batch_69e898be31448190be5ae7f5656f0497 |
completed | April 22, 2026, 9:45 a.m. |
Created at: April 16, 2026, 8:50 p.m.