Triple
T19908137
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New York, New York (song) |
E478472
|
entity |
| Predicate | musicVideoFilmingDate |
P50865
|
FINISHED |
| Object | 2001-09-07 |
—
|
LITERAL 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: 2001-09-07 | Statement: [New York, New York (song), musicVideoFilmingDate, 2001-09-07]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: musicVideoFilmingDate Context triple: [New York, New York (song), musicVideoFilmingDate, 2001-09-07]
-
A.
musicVideoDirector
Indicates that one entity is the director responsible for creating or overseeing the production of the other entity, which is a music video.
-
B.
musicVideoPremiereDate
chosen
Indicates the date on which a music video was first officially released or premiered.
-
C.
musicVideoFor
Indicates that one entity is a music video created to accompany, represent, or promote another entity, typically a song or musical work.
-
D.
musicVideoReleaseYear
Indicates the year in which a music video was officially released.
-
E.
musicVideoCameo
Indicates that one entity makes a brief or special-appearance role in the other entity’s music video.
- F. None of above.
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_69d8e520682081909892916424699bd5 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6598d91ac8190be6abdd7d1542aec |
completed | April 20, 2026, 4:51 p.m. |
| PD | Predicate disambiguation | batch_69e537ecda248190895c96afb6243823 |
completed | April 19, 2026, 8:15 p.m. |
Created at: April 10, 2026, 1:52 p.m.