Triple
T14479594
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Little Fockers |
E359063
|
entity |
| Predicate | character |
P662
|
FINISHED |
| Object | Roz Focker |
E1057064
|
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: Roz Focker | Statement: [Little Fockers, character, Roz Focker]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Roz Focker Context triple: [Little Fockers, character, Roz Focker]
-
A.
Roz Focker
chosen
Roz Focker is a free-spirited, sex-therapist mother played by Barbra Streisand in the comedy film "Meet the Fockers."
-
B.
Bernie Focker
Bernie Focker is a free-spirited, affectionate, and eccentric father portrayed by Dustin Hoffman in the comedy film "Meet the Fockers."
-
C.
Gaal Dornick
Gaal Dornick is a young mathematician and key disciple of Hari Seldon in Isaac Asimov’s Foundation series, whose involvement with psychohistory helps set the saga’s events in motion.
-
D.
Rudy Bloom
Rudy Bloom is the deceased infant son of Leopold and Molly Bloom in James Joyce’s novel "Ulysses," whose memory deeply affects his parents throughout the book.
-
E.
Conrad Dobler
Conrad Dobler was a hard-nosed NFL offensive lineman best known for his aggressive, often controversial play with the St. Louis Cardinals in the 1970s.
- 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_69d827966698819082e140837737501d |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de924a576c819098351efabdb779b1 |
completed | April 14, 2026, 7:15 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd6d8ccd608190afd23c903cd5686a |
completed | May 8, 2026, 4:58 a.m. |
Created at: April 10, 2026, 1:20 a.m.