Triple
T3592431
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Curt Gowdy |
E76055
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Geraldine Dawkins
Geraldine Dawkins is best known as the wife of famed American sportscaster Curt Gowdy.
|
E371929
|
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: Geraldine Dawkins | Statement: [Curt Gowdy, spouse, Geraldine Dawkins]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Geraldine Dawkins Context triple: [Curt Gowdy, spouse, Geraldine Dawkins]
-
A.
Bronwen Maddox
Bronwen Maddox is a British journalist and policy analyst who has held prominent leadership roles in UK public policy and media organizations.
-
B.
Philippa Giles
Philippa Giles is a British television producer best known for her work on acclaimed drama series such as Luther.
-
C.
Carobeth Laird
Carobeth Laird was an American ethnographer and linguist best known for her influential documentation of Chemehuevi language and culture.
-
D.
Ruth McCartney
Ruth McCartney is a British media and digital marketing entrepreneur and the stepsister of photographer and musician Heather McCartney, Paul McCartney’s adopted daughter.
-
E.
Ann Dummett
Ann Dummett was a British civil rights campaigner and writer known for her influential work on race relations and immigration policy in the United Kingdom.
- 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: Geraldine Dawkins Triple: [Curt Gowdy, spouse, Geraldine Dawkins]
Generated description
Geraldine Dawkins is best known as the wife of famed American sportscaster Curt Gowdy.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Geraldine Dawkins Target entity description: Geraldine Dawkins is best known as the wife of famed American sportscaster Curt Gowdy.
-
A.
Bronwen Maddox
Bronwen Maddox is a British journalist and policy analyst who has held prominent leadership roles in UK public policy and media organizations.
-
B.
Philippa Giles
Philippa Giles is a British television producer best known for her work on acclaimed drama series such as Luther.
-
C.
Carobeth Laird
Carobeth Laird was an American ethnographer and linguist best known for her influential documentation of Chemehuevi language and culture.
-
D.
Ruth McCartney
Ruth McCartney is a British media and digital marketing entrepreneur and the stepsister of photographer and musician Heather McCartney, Paul McCartney’s adopted daughter.
-
E.
Ann Dummett
Ann Dummett was a British civil rights campaigner and writer known for her influential work on race relations and immigration policy in the United Kingdom.
- 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_69ad85d8042081908af94a04c410dec0 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc15a546481909c72dac80d65e1fb |
completed | March 8, 2026, 6:35 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b4030bc5f081908d56edc4ff550d77 |
completed | March 13, 2026, 12:28 p.m. |
| NEDg | Description generation | batch_69b403c9f6788190be21ee4c849fba60 |
completed | March 13, 2026, 12:32 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69b408744dcc819081308b7182a40c88 |
completed | March 13, 2026, 12:52 p.m. |
Created at: March 8, 2026, 3:22 p.m.