Triple
T7714308
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Heat (1995 film) |
E174842
|
entity |
| Predicate | stars |
P1956
|
FINISHED |
| Object | Diane Venora |
E125516
|
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: Diane Venora | Statement: [Heat (1995 film), stars, Diane Venora]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Diane Venora Context triple: [Heat (1995 film), stars, Diane Venora]
-
A.
Diane Venora
chosen
Diane Venora is an American actress known for her intense, versatile performances in film, television, and theater, including prominent roles in works like "Heat" and "Romeo + Juliet."
-
B.
Sally Menke
Sally Menke was an American film editor best known for her long-time collaboration with director Quentin Tarantino on films such as Pulp Fiction, Kill Bill, and Inglourious Basterds.
-
C.
Leila LaSalle
Leila LaSalle is a central character in Mary Higgins Clark’s suspense novel "Weep No More, My Lady," around whom much of the mystery and intrigue revolves.
-
D.
Rosie Yormark
Rosie Yormark is the maternal grandmother of Exton Elias Downey, the son of actor Robert Downey Jr.
-
E.
Carol Vessey
Carol Vessey is a fictional high school teacher and love interest of the title character in the television series "Ed."
- 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_69c6995c463c8190a14458036249d419 |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c702ca8f048190a6ea27b8cee2f93e |
completed | March 27, 2026, 10:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c8d6ab0ab48190b273d07db6d74c33 |
completed | March 29, 2026, 7:37 a.m. |
Created at: March 27, 2026, 4:04 p.m.