Triple
T12719170
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Avi Lerner |
E303929
|
entity |
| Predicate | founded |
P104
|
FINISHED |
| Object | Nu Image |
E259306
|
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: Nu Image | Statement: [Avi Lerner, founded, Nu Image]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nu Image Context triple: [Avi Lerner, founded, Nu Image]
-
A.
Nu Image
chosen
Nu Image is a film production company known for producing a wide range of genre movies, including action, thriller, and crime dramas.
-
B.
Nu
Nu is the given name of U Nu, the first Prime Minister of independent Burma (now Myanmar) and a prominent mid-20th-century political leader.
-
C.
WireImage
WireImage is a celebrity and entertainment photography agency known for its extensive coverage of red carpet events, premieres, and industry parties.
-
D.
Neovison
Neovison is a genus of mustelid mammals best known for including the American mink, a semi-aquatic carnivore historically important in the fur trade.
-
E.
Neo
Neo is the protagonist of the science fiction film series "The Matrix," a hacker who becomes humanity's prophesied savior within a simulated reality.
- 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_69d7bdf084148190ab9d513dc0735af4 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96411d87481909127e81755f23964 |
completed | April 10, 2026, 8:56 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f67c8250108190bb7b3c93e590ea47 |
completed | May 2, 2026, 10:36 p.m. |
Created at: April 9, 2026, 5:24 p.m.