Triple
T22860590
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ken Burns |
E566908
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Olivia Burns |
—
|
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: Olivia Burns | Statement: [Ken Burns, child, Olivia Burns]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Olivia Burns Context triple: [Ken Burns, child, Olivia Burns]
-
A.
Olivia Burns
chosen
Olivia Burns is one of the children of acclaimed American documentary filmmaker Ken Burns.
-
B.
Olivia Stewart
Olivia Stewart is a film producer known for her work on literary adaptations and acclaimed independent cinema, including the screen version of Edith Wharton’s "The House of Mirth."
-
C.
Olivia Harlan
Olivia Harlan is an American sportscaster and television host known for her work as a sideline reporter on major college football and basketball broadcasts.
-
D.
Olivia Langdon
Olivia Langdon was the wife of American author Mark Twain (Samuel Clemens) and a key influence and editor of his literary work.
-
E.
Madeline O'Reilly
Madeline O'Reilly is the daughter of American television host and political commentator Bill O'Reilly.
- 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_69e24589083081908d5694c4fdc80086 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17ec082c08190943e6cfc2e25c5cc |
completed | April 29, 2026, 3:45 a.m. |
Created at: April 17, 2026, 3:37 p.m.