Triple
T6711794
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Joan Fontaine |
E153160
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Collier Young |
E510840
|
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: Collier Young | Statement: [Joan Fontaine, spouse, Collier Young]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Collier Young Context triple: [Joan Fontaine, spouse, Collier Young]
-
A.
Collier Young
chosen
Collier Young was an American screenwriter and film and television producer best known for co-creating the legal drama series "Ironside."
-
B.
Cole Young
Cole Young is a fictional mixed martial artist and the original protagonist introduced in the 2021 film adaptation of Mortal Kombat.
-
C.
Toriano Adaryll Jackson
Toriano Adaryll Jackson, better known as Tito Jackson, is an American musician and original member of the legendary Motown family group The Jackson 5.
-
D.
Harry Chandlee
Harry Chandlee was an American screenwriter and film editor best known for co-writing the Academy Award–winning World War I biographical film "Sergeant York."
-
E.
Cress Williams
Cress Williams is an American actor best known for his television roles, including the lead in the superhero series "Black Lightning" and prominent parts in shows like "Hart of Dixie" and "Prison Break."
- 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_69c68808d8d8819087369015270788fe |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d108acc08190b38b43161d8912b9 |
completed | March 27, 2026, 6:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c700924fdc8190990187fbc1b3ab20 |
completed | March 27, 2026, 10:11 p.m. |
Created at: March 27, 2026, 2:06 p.m.