Triple
T15312577
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Thomas Teller |
E366073
|
entity |
| Predicate | portrayedBy |
P1507
|
FINISHED |
| Object | Victor Newmark |
—
|
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: Victor Newmark | Statement: [John Thomas Teller, portrayedBy, Victor Newmark]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Victor Newmark Context triple: [John Thomas Teller, portrayedBy, Victor Newmark]
-
A.
Victor Newmark
chosen
Victor Newmark is a photographer known for his photographic portrayals of John Teller.
-
B.
Philip Mandelker
Philip Mandelker is a film and television producer best known for his work as an executive producer on projects such as "Something About Amelia."
-
C.
Herman Lieberman
Herman Lieberman was a prominent Polish socialist politician, lawyer, and parliamentarian active in the early 20th century, known for his leadership in the Polish left and opposition to authoritarianism.
-
D.
Morton Astrahan
Morton Astrahan was a pioneering computer scientist best known for his foundational work on IBM’s System R project, which helped establish the relational database model and SQL.
-
E.
Bernard Herzbrun
Bernard Herzbrun was an American art director known for his work on numerous Hollywood films during the 1930s and 1940s.
- 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_69d85a113ee881908e297a1d38dd79fa |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03cd2d5a88190aead748920f93d47 |
completed | April 16, 2026, 1:35 a.m. |
Created at: April 10, 2026, 3:16 a.m.