Triple
T17388358
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lauren Bacall |
E422747
|
entity |
| Predicate | father |
P120
|
FINISHED |
| Object | William Perske |
—
|
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: William Perske | Statement: [Lauren Bacall, father, William Perske]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: William Perske Context triple: [Lauren Bacall, father, William Perske]
-
A.
William Perske
chosen
William Perske was the father of acclaimed American actress Lauren Bacall, born Betty Joan Perske.
-
B.
William Perlberg
William Perlberg was a prominent American film producer active during Hollywood's studio era, known for overseeing a range of successful comedies and dramas.
-
C.
Michael Peyser
Michael Peyser is an American film and television producer known for his work on a variety of studio and independent projects.
-
D.
Joseph Weishaar
Joseph Weishaar is an American architect and designer best known for winning the competition to create the National World War I Memorial in Washington, D.C.
-
E.
Lester Persky
Lester Persky was an American film and television producer known for backing notable projects in Hollywood and independent cinema.
- 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_69d889d710288190bf0f4762801fefae |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e43a8b66288190b29bb82eff761902 |
completed | April 19, 2026, 2:14 a.m. |
Created at: April 10, 2026, 5:45 a.m.