Triple
T17763167
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Adam Arkin |
E443430
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Phyllis Lyons
Phyllis Lyons is an American actress known for her work in television and film and for her marriage to actor and director Adam Arkin.
|
E1409724
|
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: Phyllis Lyons | Statement: [Adam Arkin, spouse, Phyllis Lyons]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Phyllis Lyons Context triple: [Adam Arkin, spouse, Phyllis Lyons]
-
A.
Phyllis Miller
Phyllis Miller is an Australian local government leader who serves as the mayor of Forbes Shire in New South Wales.
-
B.
Phyllis Moore
Phyllis Moore is known as the first wife of acclaimed British comic book writer Alan Moore.
-
C.
Phyllis Allen
Phyllis Allen was an American silent film actress and comedian known for her frequent appearances in early 20th-century slapstick comedies, often alongside stars like Charlie Chaplin.
-
D.
Phyllis Ferguson
Phyllis Ferguson is known as the spouse of Canadian filmmaker and IMAX co-inventor Graeme Ferguson.
-
E.
Phyllis Browne
Phyllis Browne was a 19th-century British writer and biographer known for her popular works on notable women and domestic subjects.
- 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: Phyllis Lyons Triple: [Adam Arkin, spouse, Phyllis Lyons]
Generated description
Phyllis Lyons is an American actress known for her work in television and film and for her marriage to actor and director Adam Arkin.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Phyllis Lyons Target entity description: Phyllis Lyons is an American actress known for her work in television and film and for her marriage to actor and director Adam Arkin.
-
A.
Phyllis Miller
Phyllis Miller is an Australian local government leader who serves as the mayor of Forbes Shire in New South Wales.
-
B.
Phyllis Moore
Phyllis Moore is known as the first wife of acclaimed British comic book writer Alan Moore.
-
C.
Phyllis Allen
Phyllis Allen was an American silent film actress and comedian known for her frequent appearances in early 20th-century slapstick comedies, often alongside stars like Charlie Chaplin.
-
D.
Phyllis Ferguson
Phyllis Ferguson is known as the spouse of Canadian filmmaker and IMAX co-inventor Graeme Ferguson.
-
E.
Phyllis Browne
Phyllis Browne was a 19th-century British writer and biographer known for her popular works on notable women and domestic subjects.
- 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_69d8b9edf16c8190a59ebd245d378f4f |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e485f9fa188190aef5ffeb0b628632 |
completed | April 19, 2026, 7:36 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a081f1c707c81908de1424ba3f05828 |
completed | May 16, 2026, 7:39 a.m. |
| NEDg | Description generation | batch_6a08204234a48190b9f9a1907e9eddf6 |
completed | May 16, 2026, 7:44 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a082112e7bc8190a10cdee4571d053a |
completed | May 16, 2026, 7:47 a.m. |
Created at: April 10, 2026, 10:11 a.m.