Triple
T19191965
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lyndrea Price |
E469860
|
entity |
| Predicate | relative |
P37
|
FINISHED |
| Object | Isha Price |
—
|
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: Isha Price | Statement: [Lyndrea Price, relative, Isha Price]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Isha Price Context triple: [Lyndrea Price, relative, Isha Price]
-
A.
Isha Price
chosen
Isha Price is an American lawyer and film producer best known as the older half-sister of tennis champions Venus and Serena Williams and for her involvement in projects about their family’s story.
-
B.
Aparna Brielle
Aparna Brielle is an American actress best known for her comedic role on the NBC sitcom "A.P. Bio."
-
C.
Maya Sondhi
Maya Sondhi is a British actress and writer known for her roles in television comedies and dramas, including the BBC sitcom Citizen Khan and the crime series Line of Duty.
-
D.
Aiysha Hart
Aiysha Hart is a British-Saudi actress known for her roles in television series such as "We Are Lady Parts," "Atlantis," and "Line of Duty."
-
E.
Maya Bhaskar
Maya Bhaskar is the daughter of British comedian, writer, and actress Meera Syal.
- 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_69d8dd0ad9088190a173b32657ae2e7a |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5f8a3434881908acc4063a9ee9386 |
completed | April 20, 2026, 9:57 a.m. |
Created at: April 10, 2026, 12:07 p.m.