Triple
T4334201
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Noel Edmonds |
E97423
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Helen Soby
Helen Soby is best known as the former wife of British television presenter and media personality Noel Edmonds.
|
E470523
|
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: Helen Soby | Statement: [Noel Edmonds, spouse, Helen Soby]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Helen Soby Context triple: [Noel Edmonds, spouse, Helen Soby]
-
A.
June Hovick
June Hovick, better known as June Havoc, was an American actress, dancer, and writer whose early life as a child vaudeville performer inspired the musical "Gypsy."
-
B.
Helen Wright
Helen Wright is a wealthy, emotionally volatile socialite who becomes romantically entangled with a young violin prodigy in the film "Humoresque."
-
C.
Dorothy Goetz
Dorothy Goetz was the first wife of American composer Irving Berlin, remembered largely for her brief marriage and early death, which deeply influenced his later work.
-
D.
Jane Belson
Jane Belson was a British barrister best known as the wife of author Douglas Adams.
-
E.
Helen Hughes
Helen Hughes was a daughter of Charles Evans Hughes, the prominent American statesman who served as both U.S. Secretary of State and Chief Justice of the Supreme Court.
- 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: Helen Soby Triple: [Noel Edmonds, spouse, Helen Soby]
Generated description
Helen Soby is best known as the former wife of British television presenter and media personality Noel Edmonds.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Helen Soby Target entity description: Helen Soby is best known as the former wife of British television presenter and media personality Noel Edmonds.
-
A.
June Hovick
June Hovick, better known as June Havoc, was an American actress, dancer, and writer whose early life as a child vaudeville performer inspired the musical "Gypsy."
-
B.
Helen Wright
Helen Wright is a wealthy, emotionally volatile socialite who becomes romantically entangled with a young violin prodigy in the film "Humoresque."
-
C.
Dorothy Goetz
Dorothy Goetz was the first wife of American composer Irving Berlin, remembered largely for her brief marriage and early death, which deeply influenced his later work.
-
D.
Jane Belson
Jane Belson was a British barrister best known as the wife of author Douglas Adams.
-
E.
Helen Hughes
Helen Hughes was a daughter of Charles Evans Hughes, the prominent American statesman who served as both U.S. Secretary of State and Chief Justice of the Supreme Court.
- 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_69b3454662a481908fbcd0bbfaa3a0a4 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b351516d488190b5b3d1936e3a325d |
completed | March 12, 2026, 11:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be43821d5c8190b50e3eadabf2845b |
completed | March 21, 2026, 7:06 a.m. |
| NEDg | Description generation | batch_69be45b95ab48190b5d8b84c56b1a0ac |
completed | March 21, 2026, 7:16 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69be46e400cc8190aaa7fc42713f30c6 |
completed | March 21, 2026, 7:21 a.m. |
Created at: March 12, 2026, 11:13 p.m.