Triple
T32397727
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The River Café television series |
E827856
|
entity |
| Predicate | featuresChef |
P50761
|
FINISHED |
| Object | Ruth Rogers |
—
|
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: Ruth Rogers | Statement: [The River Café television series, featuresChef, Ruth Rogers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuresChef Context triple: [The River Café television series, featuresChef, Ruth Rogers]
-
A.
designerChef
Indicates that one entity serves as the chef responsible for designing or creating dishes, menus, or culinary concepts for another entity.
-
B.
chefTitle
Indicates that one entity holds a specific professional or honorific title in the role of a chef relative to another entity.
-
C.
chef
chosen
Indicates that one entity serves as the cook or culinary professional responsible for preparing food for another entity or context.
-
D.
visibilityOfChef
Indicates how easily or prominently a chef can be seen or observed in a given context or setting.
-
E.
chef-lieu
Indicates that one place serves as the administrative capital or main seat of government for a specified territorial division.
- F. None of above.
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_69f34919342c8190a4c3bf35a90d4e58 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_6a00d6aff0a08190a330dd0c7c1352f9 |
completed | May 10, 2026, 7:04 p.m. |
| PD | Predicate disambiguation | batch_6a00d60f2a508190aeaf5a9d8af9c39e |
completed | May 10, 2026, 7:01 p.m. |
Created at: May 1, 2026, 12:52 a.m.