Triple
T22368329
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wally Pfister |
E552969
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Anna Julien |
—
|
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: Anna Julien | Statement: [Wally Pfister, spouse, Anna Julien]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Anna Julien Context triple: [Wally Pfister, spouse, Anna Julien]
-
A.
Anna Julien
chosen
Anna Julien is the wife of American cinematographer and director Wally Pfister.
-
B.
Juliana Bordereau
Juliana Bordereau is a reclusive, elderly former lover of a famous poet whose guarded past and closely held letters drive the plot of Henry James’s novella "The Aspern Papers."
-
C.
Juliette O'Herlihy
Juliette O'Herlihy is known as the wife of Irish-American actor Gavan O'Herlihy.
-
D.
Michelle Auriol
Michelle Auriol was the wife of French politician and first President of the Fourth Republic, Vincent Auriol, and served as France’s First Lady during his presidency.
-
E.
Juliette Froissy
Juliette Froissy was the second wife of American philosopher and logician Charles Sanders Peirce, about whom relatively little biographical information is known.
- 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_69e11e4affcc8190ba7c27d29062558d |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f1580229688190a6e5e02b484033f7 |
completed | April 29, 2026, 12:59 a.m. |
Created at: April 16, 2026, 8:44 p.m.