Triple
T26284186
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Just Eat |
E661084
|
entity |
| Predicate | restaurantBenefit |
P160204
|
FINISHED |
| Object | access to online customers |
—
|
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: access to online customers | Statement: [Just Eat, restaurantBenefit, access to online customers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: restaurantBenefit Context triple: [Just Eat, restaurantBenefit, access to online customers]
-
A.
offersBuffet
Indicates that one entity provides a buffet-style service or meal option to another entity.
-
B.
restaurantContained
Indicates that a restaurant is physically located within or is a part of a larger place or establishment.
-
C.
exclusiveBenefit
Indicates that a benefit is provided to one party or group in a way that excludes others from receiving the same advantage.
-
D.
restaurantName
Indicates the name assigned to a restaurant as its identifying label.
-
E.
alsoEats
Indicates that an entity consumes something in addition to another item or items it already eats.
- 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_69ee812bbd448190be4d7478b057990a |
completed | April 26, 2026, 9:18 p.m. |
| NER | Named-entity recognition | batch_69f60e76a034819088e757b72d480585 |
completed | May 2, 2026, 2:47 p.m. |
| PD | Predicate disambiguation | batch_69f5f7ff548c8190a23e98c5e66e0bc7 |
completed | May 2, 2026, 1:11 p.m. |
| PDg | Predicate description generation | batch_69f5ffc6268c8190b63f6360ebadab73 |
completed | May 2, 2026, 1:44 p.m. |
Created at: April 26, 2026, 10:03 p.m.