Triple
T23342427
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Big House on the Hudson |
E591769
|
entity |
| Predicate | alsoKnownAs |
P39
|
FINISHED |
| Object | Sing Sing |
—
|
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: Sing Sing | Statement: [Big House on the Hudson, alsoKnownAs, Sing Sing]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sing Sing Context triple: [Big House on the Hudson, alsoKnownAs, Sing Sing]
-
A.
Sing Sing
chosen
Sing Sing is a notorious maximum-security prison in Ossining, New York, long known for housing dangerous criminals and for its historical use of the electric chair.
-
B.
Sing, Sing, Sing
"Sing, Sing, Sing" is a landmark big band jazz and swing composition, famously associated with Benny Goodman and celebrated for its driving rhythm and extended drum and clarinet solos.
-
C.
Sing It
"Sing It" is a 2012 pop single by American singer Rebecca Black that marked a more mature follow-up to her viral debut "Friday."
-
D.
Everybody Sing
Everybody Sing is a 1938 American musical comedy film starring Judy Garland as a rebellious schoolgirl with a remarkable singing talent.
-
E.
Sing It!
Sing It! is a musical comedy web series starring Debby Ryan that parodies televised singing competitions.
- 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_69e25d20e3d08190bcede87673cafb25 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f198334dec819081c432b434eb3ba5 |
completed | April 29, 2026, 5:33 a.m. |
Created at: April 17, 2026, 5:18 p.m.