Triple
T10597938
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Farrah Abraham |
E275665
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Farrah Abraham |
E275665
|
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: Farrah Abraham | Statement: [Farrah Abraham, name, Farrah Abraham]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Farrah Abraham Context triple: [Farrah Abraham, name, Farrah Abraham]
-
A.
Farrah Abraham
chosen
Farrah Abraham is an American reality television personality, author, and entrepreneur who first gained fame documenting her life as a young mother on MTV.
-
B.
Makayla Epps
Makayla Epps is an American basketball player best known for her standout collegiate career as a guard for the University of Kentucky women's basketball team.
-
C.
Laiyah Shannon Brown
Laiyah Shannon Brown is the daughter of American R&B singer Monica and former NBA player Shannon Brown.
-
D.
Amber Atkins
Amber Atkins is the ambitious small-town teenager and beauty pageant contestant portrayed by Kirsten Dunst in the dark comedy film "Drop Dead Gorgeous."
-
E.
Aisha Hinds
Aisha Hinds is an American actress known for her powerful supporting and character roles in film and television, particularly in drama and crime series.
- 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_69d6aaf948d88190806cc3a8c47a3fb2 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d6ded358248190ba9268a51b2805fc |
completed | April 8, 2026, 11:03 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d95e9c1a7c8190a91ad479518e411f |
completed | April 10, 2026, 8:33 p.m. |
Created at: April 8, 2026, 7:28 p.m.