Triple
T3764032
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sean Connery |
E82626
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Diane Cilento |
E252794
|
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 Cilento | Statement: [Sean Connery, spouse, Diane Cilento]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Diane Cilento Context triple: [Sean Connery, spouse, Diane Cilento]
-
A.
Diane Cilento
chosen
Diane Cilento was an Australian actress known for her work in British and international cinema and theatre, and for her Academy Award–nominated role in the film "Tom Jones" (1963).
-
B.
Patricia Dainton
Patricia Dainton was a British film and television actress known for her roles in 1950s and 1960s thrillers and dramas.
-
C.
Amy Jellicoe
Amy Jellicoe is the troubled, idealistic corporate employee at the center of the HBO series "Enlightened," whose spiritual awakening clashes with her self-destructive tendencies and workplace realities.
-
D.
Annette Kirwan
Annette Kirwan was the wife of prominent Irish unionist politician and barrister Edward Carson.
-
E.
Gillian Metzger
Gillian Metzger is an American legal scholar and professor known for her influential work in constitutional and administrative law.
- 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_69ad8b207b0081909d2b48843fbd8795 |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69adcbfd4be481908242c460a3f00c56 |
completed | March 8, 2026, 7:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b4f034ce008190bcae03916cfa588e |
completed | March 14, 2026, 5:20 a.m. |
Created at: March 8, 2026, 3:35 p.m.