Triple
T23062582
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Being Julia |
E574943
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Robert Lantos |
—
|
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: Robert Lantos | Statement: [Being Julia, producer, Robert Lantos]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Robert Lantos Context triple: [Being Julia, producer, Robert Lantos]
-
A.
Robert Lantos
chosen
Robert Lantos is a prominent Canadian film producer known for backing acclaimed international and independent films.
-
B.
Robert Dorfmann
Robert Dorfmann was a French film producer known for backing major European and international films, including influential works of the 1960s and 1970s.
-
C.
Robert Resnikoff
Robert Resnikoff is an American filmmaker best known for writing and directing the 1990 supernatural horror-thriller film "The First Power."
-
D.
Harvey Lichtenstein
Harvey Lichtenstein was an influential American arts administrator and long-time director of the Brooklyn Academy of Music, known for transforming it into a leading center for avant-garde performance.
-
E.
Paul Eckstein
Paul Eckstein is a television writer and producer best known for co-creating the crime drama series "Godfather of Harlem."
- 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_69e245bd6e4c8190bb8942245b68cad5 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f189a0c3c881909f137ad511c216ac |
completed | April 29, 2026, 4:31 a.m. |
Created at: April 17, 2026, 3:55 p.m.