Triple
T23191396
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tears on My Pillow |
E579744
|
entity |
| Predicate | writer |
P1360
|
FINISHED |
| Object | Al Lewis |
—
|
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: Al Lewis | Statement: [Tears on My Pillow, writer, Al Lewis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Al Lewis Context triple: [Tears on My Pillow, writer, Al Lewis]
-
A.
Al Lewis
Al Lewis is a fictional aging vaudeville comedian who is one half of a long-feuding former comedy duo in the 1975 film "The Sunshine Boys."
-
B.
Al Lewis
Al Lewis was an American character actor best known for playing Grandpa on the 1960s television sitcom "The Munsters."
-
C.
Al Lewis
chosen
Al Lewis was an American songwriter best known for co-writing popular standards such as "Blueberry Hill."
-
D.
Bill Lewis
Bill Lewis is a member of the Lewis family, known primarily in relation to that family group.
-
E.
Mel Lewis
Mel Lewis was an influential American jazz drummer and bandleader best known for co-leading the Thad Jones/Mel Lewis Orchestra, a cornerstone of modern big band jazz.
- 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_69e24600eed08190bd7e5295653a1503 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18fd777c08190bf79e38844fedf27 |
completed | April 29, 2026, 4:57 a.m. |
Created at: April 17, 2026, 4:05 p.m.