Triple
T15709591
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jean Doumanian |
E380803
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Whatever Works |
E1021901
|
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: Whatever Works | Statement: [Jean Doumanian, notableWork, Whatever Works]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Whatever Works Context triple: [Jean Doumanian, notableWork, Whatever Works]
-
A.
Whatever Works
chosen
Whatever Works is a 2009 romantic comedy film written and directed by Woody Allen, starring Larry David as a misanthropic New Yorker whose life is upended by an unexpected relationship.
-
B.
A Little Work
"A Little Work" is a pop song by Fergie from her album "Double Dutchess," noted for its autobiographical lyrics and cinematic music video depicting her struggles and recovery.
-
C.
Let’s Work
"Let’s Work" is a song by the Rolling Stones, known as a track from their 1989 album "Steel Wheels."
-
D.
Make It Work
"Make It Work" is an R&B track by Canadian duo Majid Jordan, showcasing their smooth vocals and atmospheric, synth-driven production.
-
E.
Work on It
"Work on It" is a musical track, likely a song title, referenced as part of a larger recording or album.
- 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_69d86d9bf930819082b30cf6d169297c |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e04f8d8b648190842c635f2ae7bfa4 |
completed | April 16, 2026, 2:55 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff757b7e0c81909b32aecc093c93e4 |
completed | May 9, 2026, 5:57 p.m. |
Created at: April 10, 2026, 4:45 a.m.