Triple
T13594823
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Douglas |
E324788
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Diandra Luker |
E180378
|
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: Diandra Luker | Statement: [Michael Douglas, spouse, Diandra Luker]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Diandra Luker Context triple: [Michael Douglas, spouse, Diandra Luker]
-
A.
Diandra Luker
chosen
Diandra Luker is a film producer and the former wife of American actor Michael Douglas.
-
B.
Shera Danese
Shera Danese is an American actress best known for her frequent guest appearances on the television series "Columbo" and for being the longtime wife of actor Peter Falk.
-
C.
Laura Davenport
Laura Davenport is the daughter of English actor Nigel Davenport.
-
D.
Deanna Dunagan
Deanna Dunagan is an American actress best known for her Tony Award–winning performance in the Broadway play "August: Osage County" and for her role in the horror film "The Visit."
-
E.
Laurie Johnson
Laurie Johnson is a British composer and bandleader best known for his film and television scores, including his work on the satirical Cold War film "Dr. Strangelove."
- 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_69d80769eaf081909d82f44e484d6113 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbb057f1c881909a3bb77c659a724a |
completed | April 12, 2026, 2:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe387c02108190badf9b5051cd9c7a |
completed | May 8, 2026, 7:24 p.m. |
Created at: April 9, 2026, 9:49 p.m.