Triple
T2326680
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Curtiz |
E48302
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Bess Meredyth |
E151519
|
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: Bess Meredyth | Statement: [Michael Curtiz, spouse, Bess Meredyth]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bess Meredyth Context triple: [Michael Curtiz, spouse, Bess Meredyth]
-
A.
Bess Meredyth
chosen
Bess Meredyth was an American screenwriter and silent film pioneer known for her influential work in early Hollywood cinema.
-
B.
Bess
Bess was the familiar nickname of Elizabeth "Bess" Truman, the First Lady of the United States and wife of President Harry S. Truman.
-
C.
Margaret
Margaret is a feminine given name of Greek origin, traditionally associated with the meaning "pearl" and widely used in English-speaking countries.
-
D.
Margaret
Margaret is a 2011 American drama film written and directed by Kenneth Lonergan, known for its complex portrayal of grief and moral responsibility following a tragic bus accident in New York City.
-
E.
Edith
Edith was the birth name of Edith of Scotland, an Anglo-Saxon–Norman noblewoman who became Queen consort of England as the first wife of King Henry I.
- 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_69a88aa308a88190b0b86c011fda7fce |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abc64b62a08190b5a415769ce42645 |
completed | March 7, 2026, 6:31 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae897004308190bc2e335e9caea2ca |
completed | March 9, 2026, 8:48 a.m. |
Created at: March 4, 2026, 7:50 p.m.