Triple
T8061373
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dan Dailey |
E188127
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Elizabeth Gibbons
Elizabeth Gibbons is known as the spouse of American actor Dan Dailey.
|
E727699
|
NE FINISHED |
How this triple was built (4 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: Elizabeth Gibbons | Statement: [Dan Dailey, spouse, Elizabeth Gibbons]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Elizabeth Gibbons Context triple: [Dan Dailey, spouse, Elizabeth Gibbons]
-
A.
Rosemary Forsyth
Rosemary Forsyth is a Canadian-born American actress best known for her roles in 1960s and 1970s films and television dramas.
-
B.
Anne Heywood
Anne Heywood is a British actress known for her film and television roles from the 1950s through the 1970s, often portraying strong, complex female characters.
-
C.
Mary Morris
Mary "May" Morris was a British artisan, designer, and influential figure in the Arts and Crafts movement, known especially for her innovative embroidery and textile work.
-
D.
Rebecca Giblin
Rebecca Giblin is an Australian legal scholar and advocate specializing in copyright, technology, and creators’ rights, known for her work on how digital platforms affect cultural industries.
-
E.
Maud Gernon
Maud Gernon was the wife of American lawyer and suffragist Dudley Field Malone, known primarily in historical records through this marriage.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Elizabeth Gibbons Triple: [Dan Dailey, spouse, Elizabeth Gibbons]
Generated description
Elizabeth Gibbons is known as the spouse of American actor Dan Dailey.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Elizabeth Gibbons Target entity description: Elizabeth Gibbons is known as the spouse of American actor Dan Dailey.
-
A.
Rosemary Forsyth
Rosemary Forsyth is a Canadian-born American actress best known for her roles in 1960s and 1970s films and television dramas.
-
B.
Anne Heywood
Anne Heywood is a British actress known for her film and television roles from the 1950s through the 1970s, often portraying strong, complex female characters.
-
C.
Mary Morris
Mary "May" Morris was a British artisan, designer, and influential figure in the Arts and Crafts movement, known especially for her innovative embroidery and textile work.
-
D.
Rebecca Giblin
Rebecca Giblin is an Australian legal scholar and advocate specializing in copyright, technology, and creators’ rights, known for her work on how digital platforms affect cultural industries.
-
E.
Maud Gernon
Maud Gernon was the wife of American lawyer and suffragist Dudley Field Malone, known primarily in historical records through this marriage.
- F. None of above. chosen
Provenance (5 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_69ca82b2f68881908c50560697e210da |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3fcc61c0819085edc26e75c5f6d5 |
completed | March 31, 2026, 3:30 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cdc65afac4819094282e7d63619111 |
completed | April 2, 2026, 1:28 a.m. |
| NEDg | Description generation | batch_69cdcc8439cc8190b00ce9b0781d0544 |
completed | April 2, 2026, 1:55 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69cdcdd1a0c08190aa15e665a38945e7 |
completed | April 2, 2026, 2 a.m. |
Created at: March 30, 2026, 5:26 p.m.