Triple
T22503320
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sogeti |
E556328
|
entity |
| Predicate | brandOf |
P1500
|
FINISHED |
| Object | Capgemini Group |
—
|
NE NERFINISHED |
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: Capgemini Group | Statement: [Sogeti, brandOf, Capgemini Group]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Capgemini Group Context triple: [Sogeti, brandOf, Capgemini Group]
-
A.
Capgemini
chosen
Capgemini is a global consulting, technology services, and digital transformation company headquartered in France.
-
B.
Infosys
Infosys is a leading Indian multinational IT services and consulting company known for its global technology solutions and innovation initiatives.
-
C.
Wipro Limited
Wipro Limited is a major Indian multinational information technology, consulting, and business process services company headquartered in Bengaluru.
-
D.
HCL Technologies
HCL Technologies is a global Indian IT services and consulting company known for providing software development, infrastructure management, and digital transformation solutions to enterprises worldwide.
-
E.
Atos SE
Atos SE is a French multinational information technology and digital services company known for providing consulting, systems integration, managed services, and cloud solutions worldwide.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69f15d5a01888190ba65a05616b63cbe |
completed | April 29, 2026, 1:22 a.m. |
Created at: April 16, 2026, 8:50 p.m.