Triple
T20107346
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Barking at Airplanes |
E490216
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | One Kiss |
—
|
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: One Kiss | Statement: [Barking at Airplanes, hasPart, One Kiss]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: One Kiss Context triple: [Barking at Airplanes, hasPart, One Kiss]
-
A.
One Kiss
"One Kiss" is a 2018 dance-pop and house single by Calvin Harris and Dua Lipa that became a global hit and one of the year's most successful club anthems.
-
B.
One Kiss
chosen
"One Kiss" is a song featured on the 1980 new wave album *Barking at Airplanes* by American singer-songwriter Kim Carnes.
-
C.
Just One Kiss
"Just One Kiss" is a song featured on the album "The Way I See It."
-
D.
Kissed
"Kissed" is a 1996 Canadian independent drama film, directed by Lynne Stopkewich and starring Molly Parker, that explores a young woman's fixation with death and necrophilia.
-
E.
Kiss Kiss
"Kiss Kiss" is a 2007 R&B/hip-hop single by Chris Brown featuring T-Pain, known for its catchy hook, dance-focused production, and commercial success on the Billboard charts.
- 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_69da62636cc08190982cc71733a17b8d |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e666dcb8d4819091889e19dd9137a6 |
completed | April 20, 2026, 5:48 p.m. |
Created at: April 11, 2026, 11:28 p.m.