Triple
T5120750
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jackie Sandler |
E115455
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Blended |
E392910
|
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: Blended | Statement: [Jackie Sandler, notableWork, Blended]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Blended Context triple: [Jackie Sandler, notableWork, Blended]
-
A.
Blended
chosen
Blended is a 2014 romantic comedy film starring Adam Sandler and Drew Barrymore as single parents whose disastrous blind date leads to an unexpected family vacation in Africa.
-
B.
Meantime
Meantime is Helmet’s influential 1992 heavy metal album known for its precise, riff-driven sound and impact on alternative and post-hardcore music.
-
C.
Meantime
Meantime is a 1983 British television film directed by Mike Leigh that portrays the bleak lives of a working-class family in Thatcher-era London.
-
D.
In the Mix
In the Mix is a 2005 romantic comedy-crime film starring Usher as a DJ who becomes a bodyguard entangled in a mob family's affairs.
-
E.
Flaked
Flaked is a Netflix dramedy series co-created by and starring Will Arnett as a self-help guru in Venice, California, whose carefully constructed life begins to unravel.
- 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_69bd4442ade0819087b9461f892b206b |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd78015ad88190a3e51da494c19e30 |
completed | March 20, 2026, 4:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bec4b0578c819081ad7554bafafe49 |
completed | March 21, 2026, 4:17 p.m. |
Created at: March 20, 2026, 1:42 p.m.