Triple
T37018433
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ron Capone |
E916146
|
entity |
| Predicate | workedOnRecordingOf |
P114554
|
FINISHED |
| Object | (Sittin’ On) The Dock of the Bay |
—
|
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: (Sittin’ On) The Dock of the Bay | Statement: [Ron Capone, workedOnRecordingOf, (Sittin’ On) The Dock of the Bay]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: workedOnRecordingOf Context triple: [Ron Capone, workedOnRecordingOf, (Sittin’ On) The Dock of the Bay]
-
A.
workedOnSong
chosen
Indicates that an entity contributed effort or participation to the creation, production, or performance of a particular song.
-
B.
workedOnSongFor
Indicates that one entity contributed work or effort toward creating, producing, or developing a particular song for another entity or purpose.
-
C.
recordedInWork
Indicates that an action, event, or piece of information is documented or captured within a specific work (such as a book, article, or other created resource).
-
D.
workedOnAlbum
Indicates that an entity contributed work or effort to the creation or production of a particular music album.
-
E.
workedOnSeries
Indicates that an entity contributed work to the creation or production of a particular series.
- 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_69f76e920dc48190acb6bb7ebc4dffab |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fb154c0fe08190a2e41e7a29b6055f |
completed | May 6, 2026, 10:17 a.m. |
| PD | Predicate disambiguation | batch_69f9fecc005c8190be082a8689193745 |
completed | May 5, 2026, 2:29 p.m. |
Created at: May 3, 2026, 4:14 p.m.