Triple
T14067969
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Catherine Tramell |
E338525
|
entity |
| Predicate | createdBy |
P806
|
FINISHED |
| Object | Joe Eszterhas |
E329583
|
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: Joe Eszterhas | Statement: [Catherine Tramell, createdBy, Joe Eszterhas]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Joe Eszterhas Context triple: [Catherine Tramell, createdBy, Joe Eszterhas]
-
A.
Joe Eszterhas
chosen
Joe Eszterhas is a Hungarian-American screenwriter best known for his provocative, high-profile Hollywood thrillers of the late 20th century.
-
B.
Geri Eszterhas
Geri Eszterhas is the wife of Hungarian-American screenwriter and author Joe Eszterhas.
-
C.
Lawrence Dobkin
Lawrence Dobkin was an American character actor, director, and narrator known for his prolific work in film, television, and radio from the 1940s through the 1980s.
-
D.
Gil Sharone
Gil Sharone is an American drummer known for his versatile session work and performances with bands such as Marilyn Manson, Dillinger Escape Plan, and Stolen Babies.
-
E.
Gene Corman
Gene Corman was an American film producer and talent agent known for his work in low-budget genre films and for collaborating with major studios on commercially successful projects.
- 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_69d81c67ba6c819091935650dfb3b895 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de568b81f08190a571004261c0e8e4 |
completed | April 14, 2026, 3 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fcb66aeff8819088239226bbe25fd5 |
completed | May 7, 2026, 3:57 p.m. |
Created at: April 9, 2026, 10:21 p.m.