Triple
T20372299
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jean Beauvoir |
E497093
|
entity |
| Predicate | associatedAct |
P37
|
FINISHED |
| Object | 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: Kiss | Statement: [Jean Beauvoir, associatedAct, Kiss]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kiss Context triple: [Jean Beauvoir, associatedAct, Kiss]
-
A.
Kiss
Kiss is Carly Rae Jepsen’s 2012 pop studio album that features her breakout hit “Call Me Maybe” and helped establish her international fame.
-
B.
Kiss
chosen
Kiss is an American rock band known for their elaborate stage makeup, theatrical live performances, and influential role in hard rock and heavy metal music.
-
C.
Kiss
"Kiss" is a renowned performance artwork by Tino Sehgal in which a pair of performers enact a continuous, evolving embrace that references iconic kisses from art history.
-
D.
Kiss
"Kiss" is a 1988 cover version of Prince's hit song performed by Welsh singer Tom Jones in collaboration with the band Art of Noise.
-
E.
KISS
KISS is a family of double-deck electric multiple unit trains produced by Stadler Rail for high-capacity regional and commuter 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_69e0b4a4f9b081908a5a021919c21ccb |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e678769f9c81909a52ef3c43e6064d |
completed | April 20, 2026, 7:03 p.m. |
Created at: April 16, 2026, 11:26 a.m.