Triple
T36314382
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Grady Martin |
E894148
|
entity |
| Predicate | recordLabelWorkedFor |
P196025
|
FINISHED |
| Object | Decca Records (as session musician) |
—
|
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: Decca Records (as session musician) | Statement: [Grady Martin, recordLabelWorkedFor, Decca Records (as session musician)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: recordLabelWorkedFor Context triple: [Grady Martin, recordLabelWorkedFor, Decca Records (as session musician)]
-
A.
recordLabelAssociated
Indicates that one entity (typically an artist or release) is or has been signed to, released under, or otherwise officially affiliated with a particular record label.
-
B.
hasRecordLabel
Indicates that an entity (typically a musical artist or release) is associated with or signed to a particular record label.
-
C.
ownedRecordLabel
Indicates that one entity previously possessed legal ownership or controlling interest in a particular record label.
-
D.
recordLabelHeadquartersOf
Indicates that a particular location serves as the main headquarters of a specific record label.
-
E.
hasFictionalRecordLabel
Indicates that an entity is associated with a record label that exists only within a fictional or narrative context.
- F. None of above. chosen
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_69f76e4d1a788190a6ab6ccca28547a7 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fe00dad1708190b6522476bebb43af |
completed | May 8, 2026, 3:27 p.m. |
| PD | Predicate disambiguation | batch_69fdfc3717f48190bb50ac2919c8ef95 |
completed | May 8, 2026, 3:07 p.m. |
| PDg | Predicate description generation | batch_69fe00d8d8248190a63c12aa2c2f7c0c |
completed | May 8, 2026, 3:27 p.m. |
Created at: May 3, 2026, 4:09 p.m.