Triple
T19872289
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Number One with a Bullet |
E477547
|
entity |
| Predicate | hasCastMember |
P2308
|
FINISHED |
| Object | Mykelti Williamson |
—
|
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: Mykelti Williamson | Statement: [Number One with a Bullet, hasCastMember, Mykelti Williamson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mykelti Williamson Context triple: [Number One with a Bullet, hasCastMember, Mykelti Williamson]
-
A.
Mykelti Williamson
chosen
Mykelti Williamson is an American actor best known for his roles in films such as "Forrest Gump," where he played Bubba, and numerous television series.
-
B.
Tyrel Jackson Williams
Tyrel Jackson Williams is an American actor best known for his roles on the Disney XD series "Lab Rats" and the IFC comedy "Brockmire."
-
C.
Delano Williams
Delano Williams is a sprinter from the Turks and Caicos Islands who has represented Great Britain in international track and field competitions.
-
D.
Bryant Myers
Bryant Myers is a Puerto Rican Latin trap and reggaeton artist known for his gritty lyrics and collaborations with major urban artists.
-
E.
Micayle McKinney
Micayle McKinney is an author known for writing the work titled "Damaged."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e51e7d948190aedbcd6c30361c39 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e658d826f88190be04188997952d1b |
completed | April 20, 2026, 4:48 p.m. |
Created at: April 10, 2026, 1:51 p.m.