Triple
T21481756
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marc Platt |
E530009
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Tonight and Every Night |
—
|
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: Tonight and Every Night | Statement: [Marc Platt, notableWork, Tonight and Every Night]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tonight and Every Night Context triple: [Marc Platt, notableWork, Tonight and Every Night]
-
A.
Tonight and Every Night
chosen
Tonight and Every Night is a 1945 Technicolor musical film starring Rita Hayworth, set in wartime London and loosely inspired by the real-life Windmill Theatre.
-
B.
Every Night
"Every Night" is a song featured on the soundtrack of the 1936 musical film "Anything Goes."
-
C.
Every Night
"Every Night" is a song by the punk rock band Screeching Weasel from their 1993 album *Anthem for a New Tomorrow*.
-
D.
Every Night
"Every Night" is a song by the punk rock band SNFU from their 1986 album "How to Make Enemies and Irritate People."
-
E.
Every Single Night
"Every Single Night" is an introspective, avant-pop song by American singer-songwriter Fiona Apple, known for its intricate lyrics and unconventional musical structure.
- 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_69e0c45acc3881908e38d3f28964152b |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9ea338f988190a3044f8d02a567fe |
completed | April 23, 2026, 9:45 a.m. |
Created at: April 16, 2026, 6:21 p.m.