Triple
T31289465
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TAFKAP |
E797893
|
entity |
| Predicate | refersToPersonBirthName |
P80791
|
FINISHED |
| Object | Prince Rogers Nelson |
—
|
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: Prince Rogers Nelson | Statement: [TAFKAP, refersToPersonBirthName, Prince Rogers Nelson]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: refersToPersonBirthName Context triple: [TAFKAP, refersToPersonBirthName, Prince Rogers Nelson]
-
A.
appliesToPersonBirthName
Indicates that the referenced value is used as the birth name of the specified person.
-
B.
bearerBirthNameOf
chosen
Indicates that one entity is the birth name originally given to and borne by another entity.
-
C.
honoursPersonBirthName
Indicates that an entity formally recognizes or commemorates a person using the name they were given at birth.
-
D.
portraysCharacterBirthName
Indicates that one entity depicts or represents the birth name of a character associated with another entity.
-
E.
portrayedByBirthName
Indicates that a role or character is portrayed by a person identified specifically by their birth name rather than a stage or alternate name.
- 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_69f224dfde288190af313f3c221c857e |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69fd37b695c88190855801626f91c4cd |
completed | May 8, 2026, 1:09 a.m. |
| PD | Predicate disambiguation | batch_69fd374cccf08190a230e87164af5938 |
completed | May 8, 2026, 1:07 a.m. |
Created at: April 29, 2026, 9:14 p.m.