Triple
T23250963
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TV total |
E581728
|
entity |
| Predicate | hasSpinOff |
P7226
|
FINISHED |
| Object | TV total Autoball |
—
|
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: TV total Autoball | Statement: [TV total, hasSpinOff, TV total Autoball]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: TV total Autoball Context triple: [TV total, hasSpinOff, TV total Autoball]
-
A.
TV total
chosen
TV total is a popular German late-night comedy and talk show hosted by Stefan Raab that aired on the ProSieben television network.
-
B.
All That Sports
All That Sports is a South Korean sports management agency best known for representing Olympic figure skating champion Yuna Kim.
-
C.
TV 2 Play
TV 2 Play is the Norwegian broadcaster TV 2’s streaming service, offering on-demand access to its TV channels, series, films, and live sports online.
-
D.
Teledeporte
Teledeporte is a Spanish public television channel dedicated to sports programming, offering live broadcasts and coverage of national and international sporting events.
-
E.
Television Knockout
Television Knockout is a brand name likely associated with high-impact, attention-grabbing television content or services.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e24606b17c81908aba1a4911c8a8ba |
completed | April 17, 2026, 2:39 p.m. |
| NER | Named-entity recognition | batch_69f193f5aa9081909775fb7f7dc660b3 |
completed | April 29, 2026, 5:15 a.m. |
Created at: April 17, 2026, 4:10 p.m.