Triple
T16721451
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bill Pullman |
E406357
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | While You Were Sleeping |
E406359
|
NE FINISHED |
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: While You Were Sleeping | Statement: [Bill Pullman, notableWork, While You Were Sleeping]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: While You Were Sleeping Context triple: [Bill Pullman, notableWork, While You Were Sleeping]
-
A.
While You Were Sleeping
chosen
While You Were Sleeping is a 1995 romantic comedy film starring Sandra Bullock as a lonely transit worker who saves her crush and becomes entangled with his family while he is in a coma.
-
B.
Sweetnighter
Sweetnighter is a 1973 jazz fusion album by Weather Report that marked the band’s shift toward a funkier, groove-oriented sound.
-
C.
Bedtime
"Bedtime" is a British television drama series best known for its intimate, character-driven stories set around the lives of neighbors in a suburban street at night.
-
D.
She Only Sleeps
"She Only Sleeps" is a song by Danish musician and composer Efterklang from their album "Grown Backwards."
-
E.
Sleep on It
"Sleep on It" is a song by American R&B singer Chaka Khan.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d8838f242881908abd8bc138795886 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e38743750c81908a980372ad8f1a6a |
completed | April 18, 2026, 1:29 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a009d41cb6c8190bfa164ad20f009d9 |
completed | May 10, 2026, 2:59 p.m. |
Created at: April 10, 2026, 5:20 a.m.