Triple
T19200926
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mean Mr. Mustard |
E470103
|
entity |
| Predicate | sequenceInMedley |
P87551
|
FINISHED |
| Object | third song in Abbey Road medley |
—
|
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: third song in Abbey Road medley | Statement: [Mean Mr. Mustard, sequenceInMedley, third song in Abbey Road medley]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sequenceInMedley Context triple: [Mean Mr. Mustard, sequenceInMedley, third song in Abbey Road medley]
-
A.
isMedleyWith
Indicates that two or more musical pieces are combined and performed together as a continuous medley.
-
B.
songPerformedInSequence
chosen
Indicates that a song is performed as part of a specific ordered sequence of performances or musical pieces.
-
C.
sequenceInCategory
Indicates that one entity occurs as an ordered element within a specific category or grouping of items.
-
D.
sequenceWith
Indicates that one entity occurs in a specific order directly before or after another entity as part of a defined sequence.
-
E.
albumSequence
Indicates that one album directly follows another in a defined ordered sequence, such as a discography or 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_69d8dd0ad9088190a173b32657ae2e7a |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5f997879c8190ae7618d1ba0cede9 |
completed | April 20, 2026, 10:01 a.m. |
| PD | Predicate disambiguation | batch_69e4b9bc158081908307dab01d9478c6 |
completed | April 19, 2026, 11:17 a.m. |
Created at: April 10, 2026, 12:07 p.m.