Triple
T33966238
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tommy Sweet |
E870860
|
entity |
| Predicate | formerProtégéOf |
P201349
|
FINISHED |
| Object | Bad Blake |
—
|
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: Bad Blake | Statement: [Tommy Sweet, formerProtégéOf, Bad Blake]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerProtégéOf Context triple: [Tommy Sweet, formerProtégéOf, Bad Blake]
-
A.
formerBandmateOf
Indicates that two people were once members of the same band but are no longer bandmates.
-
B.
recordingArtistLaterKnownAs
Indicates that the subject is a recording artist who was later known by the name or identity represented by the object.
-
C.
hasRapAlterEgoOf
Indicates that one entity is the rap-stage persona or alter ego used by another entity.
-
D.
parentArtist
Indicates that one artist is the parent (biological, adoptive, or otherwise recognized) of another artist.
-
E.
notableFormerArtist
Indicates that the subject was previously an artist associated with the object and is recognized as notable in that former artistic role.
- 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_69f3499ce8e88190b66e1d49ad8c7037 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69ffecdcbac4819093b725a7dbe0e61b |
completed | May 10, 2026, 2:26 a.m. |
| PD | Predicate disambiguation | batch_69ffec3633288190adbbd84e277708dc |
completed | May 10, 2026, 2:23 a.m. |
| PDg | Predicate description generation | batch_69ffecdbe62081909f901e7d4db69d60 |
completed | May 10, 2026, 2:26 a.m. |
Created at: May 1, 2026, 1:50 a.m.