Triple
T15584278
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pootie Tang |
E374577
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Ali LeRoi |
E864782
|
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: Ali LeRoi | Statement: [Pootie Tang, producer, Ali LeRoi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ali LeRoi Context triple: [Pootie Tang, producer, Ali LeRoi]
-
A.
Ali LeRoi
chosen
Ali LeRoi is an American television writer, producer, and director best known for co-creating the sitcom "Everybody Hates Chris" and his collaborations with comedian Chris Rock.
-
B.
Leroy Romans
Leroy Romans is a songwriter best known for co-writing Drake's global hit single "One Dance."
-
C.
Allen Passalaqua
Allen Passalaqua is a professional comic book colorist known for his work on titles such as *Godzilla: Aftershock*.
-
D.
Roby Marshall
Roby Marshall is the husband of American actress Tracey Gold, known for her role on the sitcom "Growing Pains."
-
E.
Mat Rogers
Mat Rogers is an Australian former dual-code rugby international who played both rugby league and rugby union at elite levels, including representing Australia and starring in the NRL.
- 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_69d85ccd575081908909b71a3f3e3a61 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04e47971481909e986dd999354628 |
completed | April 16, 2026, 2:49 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff4c4f71e48190a15eb0a2138f083f |
completed | May 9, 2026, 3:01 p.m. |
Created at: April 10, 2026, 4:11 a.m.