Triple
T36327137
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Greatest Hits |
E894511
|
entity |
| Predicate | includesNewRecordingOf |
P144119
|
FINISHED |
| Object | Carolina in My Mind |
E258838
|
NE 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: Carolina in My Mind | Statement: [Greatest Hits, includesNewRecordingOf, Carolina in My Mind]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: includesNewRecordingOf Context triple: [Greatest Hits, includesNewRecordingOf, Carolina in My Mind]
-
A.
includesNewRecordings
chosen
Indicates that one entity contains or incorporates newly created or previously unreleased recordings of another entity.
-
B.
includedOnReRecording
Indicates that something (such as a part, element, or contribution) is present or used again on a subsequent re-recorded version of a work.
-
C.
recordingOf
Indicates that one entity is an audio or video capture or performance that documents, represents, or preserves another entity (such as a work, event, or expression).
-
D.
hasRe-recording
Indicates that one recording is a new or updated version made again from the same original material or performance.
-
E.
reRecording
Indicates that an existing recording is being recorded again, such as duplicating, redoing, or capturing a new version of previously recorded material.
- F. None of above.
Provenance (4 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_69f76e4dcf088190a6c3216c209cab52 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a037c8d06cc8190ab6a5e18d9d2571e |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a39a31abdc8819081d647a410609572 |
completed | June 22, 2026, 9:03 p.m. |
| PD | Predicate disambiguation | batch_6a037a0a54cc8190868c1bfa1590d1a6 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:09 p.m.