Triple
T7714351
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Far from Heaven |
E174843
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Christine Vachon |
E445223
|
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: Christine Vachon | Statement: [Far from Heaven, producer, Christine Vachon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Christine Vachon Context triple: [Far from Heaven, producer, Christine Vachon]
-
A.
Christine Vachon
chosen
Christine Vachon is an influential American independent film producer and co-founder of Killer Films, known for championing bold, queer, and auteur-driven cinema.
-
B.
Christine Gossett
Christine Gossett was the wife of American character actor Leon Ames, known primarily in relation to his long marriage and family life.
-
C.
Mary LaRoche
Mary LaRoche was an American actress and singer known for her work in mid-20th-century film, television, and Broadway productions.
-
D.
Diane Burgdorf
Diane Burgdorf is the wife of Mark Thatcher, the son of former British Prime Minister Margaret Thatcher.
-
E.
Christine Nagel
Christine Nagel is a renowned Swiss perfumer celebrated for creating numerous successful designer and niche fragrances for major luxury brands.
- 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_69cf275f49f48190ad92d5aaebaac4d0 |
completed | April 3, 2026, 2:35 a.m. |
Created at: March 27, 2026, 4:04 p.m.