Triple
T19111085
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stefani Germanotta |
E467789
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Poker Face |
—
|
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: Poker Face | Statement: [Stefani Germanotta, notableWork, Poker Face]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Poker Face Context triple: [Stefani Germanotta, notableWork, Poker Face]
-
A.
Poker Face
"Poker Face" is a 2023 American mystery-of-the-week television series created by Rian Johnson and starring Natasha Lyonne as a human lie detector who solves murders while on the run.
-
B.
Poker Face
chosen
"Poker Face" is a globally successful electropop single by Lady Gaga, widely recognized as one of her signature hits and a defining song of late-2000s pop music.
-
C.
Sit on My Face
"Sit on My Face" is a bawdy comedic song by the British surreal comedy group Monty Python, known for its explicit innuendo and satirical take on sexual themes.
-
D.
Say It To My Face
"Say It To My Face" is a track by Chicago rapper Lil Durk featured on his mixtape series "Signed to the Streets."
-
E.
I'm the Face
"I'm the Face" is an early 1964 single by the English rock band The Who (then known as The High Numbers), reflecting their Mod-era rhythm and blues style.
- 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_69d8dd06a26481908039e2a1bae8c597 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e393bafc81908e35a0eba7b807a6 |
completed | April 20, 2026, 8:28 a.m. |
Created at: April 10, 2026, 12:04 p.m.