Triple
T3329107
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rebbie Jackson |
E69990
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object |
Austin Brown
Austin Brown is an American singer-songwriter and producer, and the son of Rebbie Jackson from the Jackson musical family.
|
E352136
|
NE FINISHED |
How this triple was built (4 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: Austin Brown | Statement: [Rebbie Jackson, child, Austin Brown]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Austin Brown Context triple: [Rebbie Jackson, child, Austin Brown]
-
A.
Jacob Brown
Jacob Brown was a prominent U.S. Army general in the War of 1812, noted for his leadership and tactical skill in major engagements against British forces.
-
B.
Ryan Brown
Ryan Brown is a film editor known for his work on the movie "Horse Girl."
-
C.
Jonathan Brown
Jonathan Brown is a cinematographer best known for his work on major studio comedies and mainstream Hollywood films, including the 2006 reboot of The Pink Panther.
-
D.
Kevin Liles
Kevin Liles is an American music executive and entrepreneur best known for his leadership roles at Def Jam Recordings and later at Warner Music Group.
-
E.
Michael Jenkins
Michael Jenkins is an Australian screenwriter and director known for his work in film and television, including influential Australian dramas.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Austin Brown Triple: [Rebbie Jackson, child, Austin Brown]
Generated description
Austin Brown is an American singer-songwriter and producer, and the son of Rebbie Jackson from the Jackson musical family.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Austin Brown Target entity description: Austin Brown is an American singer-songwriter and producer, and the son of Rebbie Jackson from the Jackson musical family.
-
A.
Jacob Brown
Jacob Brown was a prominent U.S. Army general in the War of 1812, noted for his leadership and tactical skill in major engagements against British forces.
-
B.
Ryan Brown
Ryan Brown is a film editor known for his work on the movie "Horse Girl."
-
C.
Jonathan Brown
Jonathan Brown is a cinematographer best known for his work on major studio comedies and mainstream Hollywood films, including the 2006 reboot of The Pink Panther.
-
D.
Kevin Liles
Kevin Liles is an American music executive and entrepreneur best known for his leadership roles at Def Jam Recordings and later at Warner Music Group.
-
E.
Michael Jenkins
Michael Jenkins is an Australian screenwriter and director known for his work in film and television, including influential Australian dramas.
- F. None of above. chosen
Provenance (5 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_69ad85a24f208190bcf83131bfed3521 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb1708b908190bc5c4122623d9b77 |
completed | March 8, 2026, 5:27 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b32510c4f88190972b1a1bcce16a9d |
completed | March 12, 2026, 8:41 p.m. |
| NEDg | Description generation | batch_69b33021ec5c819087017500a47ff912 |
completed | March 12, 2026, 9:29 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69b3307db970819094854583d61e948e |
completed | March 12, 2026, 9:30 p.m. |
Created at: March 8, 2026, 3:12 p.m.