Triple
T22797677
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Konnie Huq |
E564292
|
entity |
| Predicate | endTimeOfRole:Blue Peter presenter |
P49050
|
FINISHED |
| Object | 2008 |
—
|
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: 2008 | Statement: [Konnie Huq, endTimeOfRole:Blue Peter presenter, 2008]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: endTimeOfRole:Blue Peter presenter Context triple: [Konnie Huq, endTimeOfRole:Blue Peter presenter, 2008]
-
A.
presenterOccupation
Indicates that an entity serves in a specific professional role or job as a presenter.
-
B.
titleEndedOn
chosen
Indicates that a particular title or position held by an entity ceased or officially ended on a specified date.
-
C.
NicholasParsonsTenure
Indicates the period during which Nicholas Parsons held a particular position, role, or office.
-
D.
formerCoHostOf
Indicates that one entity previously served as a co-host together with another entity, but no longer holds that co-hosting role.
-
E.
mediaRole
Indicates the specific function, capacity, or position an entity holds in relation to a media item (such as creator, editor, performer, or distributor).
- 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_69e2458185f88190b0045227ee420411 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17cda76448190891c5190e1d75ae0 |
completed | April 29, 2026, 3:36 a.m. |
| PD | Predicate disambiguation | batch_69eed2c32e8c8190b73bb9965ed47d64 |
completed | April 27, 2026, 3:06 a.m. |
Created at: April 17, 2026, 3:30 p.m.