Triple
T4423303
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Daniel Radcliffe |
E95151
|
entity |
| Predicate | parent |
P120
|
FINISHED |
| Object |
Marcia Gresham
Marcia Gresham is a British casting director best known as the mother of actor Daniel Radcliffe.
|
E649772
|
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: Marcia Gresham | Statement: [Daniel Radcliffe, parent, Marcia Gresham]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marcia Gresham Context triple: [Daniel Radcliffe, parent, Marcia Gresham]
-
A.
Marcia Harvey
Marcia Harvey is an American author and the first wife of comedian and television host Steve Harvey, known for her poetry and writings on life, faith, and relationships.
-
B.
Marcia Rieke
Marcia Rieke is an American astronomer renowned for her leadership in infrared instrumentation and her key role in developing the James Webb Space Telescope.
-
C.
Marcia Warren
Marcia Warren is an English actress known for her extensive work in television, film, and theatre, often in comedic and character roles.
-
D.
Gail Gregg
Gail Gregg is an American artist and journalist known for her work in visual arts and for her connection to the prominent Sulzberger publishing family.
-
E.
Marcia Manon
Marcia Manon was a silent film actress active in the 1910s and 1920s, known for her supporting roles in American dramas and melodramas.
- 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: Marcia Gresham Triple: [Daniel Radcliffe, parent, Marcia Gresham]
Generated description
Marcia Gresham is a British casting director best known as the mother of actor Daniel Radcliffe.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Marcia Gresham Target entity description: Marcia Gresham is a British casting director best known as the mother of actor Daniel Radcliffe.
-
A.
Marcia Harvey
Marcia Harvey is an American author and the first wife of comedian and television host Steve Harvey, known for her poetry and writings on life, faith, and relationships.
-
B.
Marcia Rieke
Marcia Rieke is an American astronomer renowned for her leadership in infrared instrumentation and her key role in developing the James Webb Space Telescope.
-
C.
Marcia Warren
Marcia Warren is an English actress known for her extensive work in television, film, and theatre, often in comedic and character roles.
-
D.
Gail Gregg
Gail Gregg is an American artist and journalist known for her work in visual arts and for her connection to the prominent Sulzberger publishing family.
-
E.
Marcia Manon
Marcia Manon was a silent film actress active in the 1910s and 1920s, known for her supporting roles in American dramas and melodramas.
- 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_69b3453a36908190b95a79a297ca083c |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b3554b36a48190a475ac5474bed132 |
completed | March 13, 2026, 12:07 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7cb9f421081908b9df22decae8923 |
completed | March 28, 2026, 12:37 p.m. |
| NEDg | Description generation | batch_69c7ccafd63c81908e5eab61ed615180 |
completed | March 28, 2026, 12:42 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69c7cd9966e481909eb3c23bb59777d9 |
completed | March 28, 2026, 12:46 p.m. |
Created at: March 12, 2026, 11:30 p.m.