Triple
T9780542
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frankie Faison |
E237357
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Faison |
E231116
|
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: Faison | Statement: [Frankie Faison, familyName, Faison]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Faison Context triple: [Frankie Faison, familyName, Faison]
-
A.
Faison
chosen
Faison is a surname most notably associated with American actor and comedian Donald Faison.
-
B.
Conetoe
Conetoe is a small rural town located in Edgecombe County in eastern North Carolina, United States.
-
C.
Guiteau
Guiteau is the surname of Charles J. Guiteau, the American lawyer and assassin who killed U.S. President James A. Garfield in 1881.
-
D.
Big Hawk
Big Hawk was a Houston-based rapper and member of the Screwed Up Click, known for his influential role in the Southern hip hop scene.
-
E.
Moultrie
Moultrie is a surname most notably associated with William Moultrie, an American Revolutionary War general and political leader from South Carolina.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca84d975a08190aab25b02a89bdab3 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cda1b0b15881909ef52d0156148c59 |
completed | April 1, 2026, 10:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1bd28b0e48190984cf44d88f324d7 |
completed | April 5, 2026, 1:38 a.m. |
Created at: March 30, 2026, 8:27 p.m.