Triple
T18164979
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mirror Group Newspapers |
E434868
|
entity |
| Predicate | hasSubsidiary |
P254
|
FINISHED |
| Object | MGN Limited |
—
|
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: MGN Limited | Statement: [Mirror Group Newspapers, hasSubsidiary, MGN Limited]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MGN Limited Context triple: [Mirror Group Newspapers, hasSubsidiary, MGN Limited]
-
A.
MGN Limited
chosen
MGN Limited is a British media company best known as the publisher of the Daily Mirror and other national newspapers and magazines.
-
B.
Assmang Limited
Assmang Limited is a South African mining company known for producing iron ore, manganese and chrome ores, and related alloys for global markets.
-
C.
Margo Lion Ltd.
Margo Lion Ltd. is a production company associated with theater and entertainment producer Margo Lion.
-
D.
Mace Group
Mace Group is a global construction and consultancy company known for delivering major complex projects, including high-profile sports stadiums and landmark buildings.
-
E.
Gwynnes Limited
Gwynnes Limited was a British engineering firm best known for producing aircraft engines and pumps in the early 20th century.
- 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_69d8b90b7a188190b3fc7b8d4a6cd20a |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4dec71b7881908d123d0cea3adf1f |
completed | April 19, 2026, 1:55 p.m. |
Created at: April 10, 2026, 10:30 a.m.