Triple
T31514773
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Haji-Ioannou family |
E804036
|
entity |
| Predicate | ownsBrandPortfolio |
P171719
|
FINISHED |
| Object | easyGroup brand family |
—
|
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: easyGroup brand family | Statement: [Haji-Ioannou family, ownsBrandPortfolio, easyGroup brand family]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ownsBrandPortfolio Context triple: [Haji-Ioannou family, ownsBrandPortfolio, easyGroup brand family]
-
A.
partOfBrandPortfolioOf
Indicates that one brand is included within, and belongs to, the overall brand portfolio of another entity.
-
B.
brandPortfolioSize
Indicates the number of distinct brands included within an entity’s overall brand portfolio.
-
C.
positionInBrandPortfolio
Indicates the relative role or rank that a brand holds within a company’s overall brand portfolio.
-
D.
brandOrPortal
Indicates that one entity functions as a brand or a branded portal associated with another entity.
-
E.
associatedBrandCollection
Indicates a relationship where one or more brands are grouped or linked together as part of a specific collection.
- F. None of above. chosen
Provenance (4 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_69f348ceb0a48190ae7feca263b6296c |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6a2578cb081908304c8d338fb5b81 |
completed | May 3, 2026, 1:18 a.m. |
| PD | Predicate disambiguation | batch_69f69fe82e5c81909da9db0a2f3bba6d |
completed | May 3, 2026, 1:07 a.m. |
| PDg | Predicate description generation | batch_69f6a0e920cc8190a943fdd0594906c5 |
completed | May 3, 2026, 1:12 a.m. |
Created at: April 30, 2026, 9:52 p.m.