Triple
T15715158
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Buzz Harper |
E380941
|
entity |
| Predicate | livesWith |
P4704
|
FINISHED |
| Object | Sonja Harper |
E391214
|
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: Sonja Harper | Statement: [Buzz Harper, livesWith, Sonja Harper]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sonja Harper Context triple: [Buzz Harper, livesWith, Sonja Harper]
-
A.
Sonja Harper
chosen
Sonja Harper is a teenage granddaughter in the sitcom "Mama’s Family," known for her rebellious streak and frequent clashes with her sharp-tongued grandmother, Thelma Harper.
-
B.
Sonja Hood
Sonja Hood is an Australian sports administrator who serves as the president of the North Melbourne Football Club in the Australian Football League.
-
C.
Paula Harper
Paula Harper is a fictional character appearing in the narrative work "The Masks."
-
D.
Susannah Shipman
Susannah Shipman is a film producer best known for her work on the Academy Award–winning documentary "Taxi to the Dark Side."
-
E.
Elaine Harper
Elaine Harper is a young minister's daughter and the fiancée of drama critic Mortimer Brewster in the dark comedic play "Arsenic and Old Lace."
- 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_69d86d9bf930819082b30cf6d169297c |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e04f90aea0819082a9e9fe0f7780b0 |
completed | April 16, 2026, 2:55 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff997fe6f48190813bde2bfc11c253 |
completed | May 9, 2026, 8:30 p.m. |
Created at: April 10, 2026, 4:45 a.m.