Triple
T23250879
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | waipu.tv |
E581726
|
entity |
| Predicate | competitor |
P1375
|
FINISHED |
| Object | Zattoo |
—
|
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: Zattoo | Statement: [waipu.tv, competitor, Zattoo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Zattoo Context triple: [waipu.tv, competitor, Zattoo]
-
A.
Zattoo
chosen
Zattoo is an internet-based live TV and streaming platform that allows users to watch television channels online across various devices.
-
B.
Duolingo
Duolingo is a popular language-learning platform and app known for its gamified lessons and wide range of courses accessible for free.
-
C.
Everglot
Everglot is the aristocratic family surname of Victoria in Tim Burton’s animated film "Corpse Bride."
-
D.
Teachme
Teachme is a popular R&B song written and produced by Carvin Haggins, best known through its recording by the group Musiq Soulchild.
-
E.
Skillzy
Skillzy is the official mascot of UEFA Euro 2020, depicted as a freestyle footballer character used to promote the tournament and engage fans.
- 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.