Triple
T36749381
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pat and Margaret |
E907861
|
entity |
| Predicate | screenDebutOnChannel |
P175829
|
FINISHED |
| Object | BBC One |
—
|
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: BBC One | Statement: [Pat and Margaret, screenDebutOnChannel, BBC One]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: screenDebutOnChannel Context triple: [Pat and Margaret, screenDebutOnChannel, BBC One]
-
A.
screenDebut
Indicates the event or relationship in which an entity appears on screen for the first time in a film, television, or other visual media production.
-
B.
debutChannel
chosen
Indicates the channel or platform on which something (such as a work, performance, or content) is first publicly released or introduced.
-
C.
channelNumber
Indicates the specific numeric identifier assigned to a channel within a system or medium.
-
D.
formerChannelNumber
Indicates that an entity was previously assigned or used a particular channel number before a change to its current channel designation.
-
E.
firstAiredOnChannel
Indicates the original broadcast channel on which a program or episode was first aired.
- 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_69f76e76d10881909ec1679bc043108c |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fba2877b248190a974eb092243c0c4 |
completed | May 6, 2026, 8:20 p.m. |
| PD | Predicate disambiguation | batch_69fb8d06a1b48190a937aa410d159dfa |
completed | May 6, 2026, 6:48 p.m. |
Created at: May 3, 2026, 4:12 p.m.