Triple
T6804654
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John de Mol |
E156272
|
entity |
| Predicate | founded |
P104
|
FINISHED |
| Object | Talpa Media |
E140756
|
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: Talpa Media | Statement: [John de Mol, founded, Talpa Media]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Talpa Media Context triple: [John de Mol, founded, Talpa Media]
-
A.
Talpa Media
chosen
Talpa Media is a Dutch television production company best known for creating international reality and talent show formats such as "The Voice."
-
B.
Talpa Global
Talpa Global is the international distribution and licensing arm of Talpa Media, responsible for bringing its television formats and content to markets worldwide.
-
C.
Talpa Productions
Talpa Productions is a Dutch television production company best known for creating internationally successful reality and talent show formats.
-
D.
PubMatic
PubMatic is a digital advertising technology company that provides a sell-side platform (SSP) enabling publishers to manage and optimize programmatic ad inventory and revenue.
-
E.
Omnilab Media
Omnilab Media is an Australian film and television production and post-production company involved in financing and producing feature films and other screen content.
- 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_69c68826e6a48190a3d220b541e639de |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d2ea459c819095388218d53c250a |
completed | March 27, 2026, 6:56 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c71a9ff30c8190aaf2687dd41fc07a |
completed | March 28, 2026, 12:02 a.m. |
Created at: March 27, 2026, 2:16 p.m.