Triple
T11859461
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Feud: Bette and Joan |
E282121
|
entity |
| Predicate | coCreator |
P7732
|
FINISHED |
| Object |
Michael Zam
Michael Zam is a screenwriter and producer best known for co-creating the acclaimed television miniseries "Feud: Bette and Joan."
|
E951505
|
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: Michael Zam | Statement: [Feud: Bette and Joan, coCreator, Michael Zam]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michael Zam Context triple: [Feud: Bette and Joan, coCreator, Michael Zam]
-
A.
Michael Lark
Michael Lark is an American comic book artist best known for his gritty, realistic artwork on series such as Gotham Central, Daredevil, and Lazarus.
-
B.
Colin Donnell
Colin Donnell is an American actor best known for his television roles in series such as "Arrow" and "Chicago Med," as well as his work on Broadway.
-
C.
Gene Draper
Gene Draper is the infant son of Don and Betty Draper on the television series "Mad Men," named after Betty's late father.
-
D.
Vincent Kartheiser
Vincent Kartheiser is an American actor best known for his role as ambitious ad executive Pete Campbell on the television series "Mad Men."
-
E.
Jesse Macht
Jesse Macht is an American singer-songwriter and musician known for his melodic pop-rock style and work as a solo artist and band member.
- 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: Michael Zam Triple: [Feud: Bette and Joan, coCreator, Michael Zam]
Generated description
Michael Zam is a screenwriter and producer best known for co-creating the acclaimed television miniseries "Feud: Bette and Joan."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Michael Zam Target entity description: Michael Zam is a screenwriter and producer best known for co-creating the acclaimed television miniseries "Feud: Bette and Joan."
-
A.
Michael Lark
Michael Lark is an American comic book artist best known for his gritty, realistic artwork on series such as Gotham Central, Daredevil, and Lazarus.
-
B.
Colin Donnell
Colin Donnell is an American actor best known for his television roles in series such as "Arrow" and "Chicago Med," as well as his work on Broadway.
-
C.
Gene Draper
Gene Draper is the infant son of Don and Betty Draper on the television series "Mad Men," named after Betty's late father.
-
D.
Vincent Kartheiser
Vincent Kartheiser is an American actor best known for his role as ambitious ad executive Pete Campbell on the television series "Mad Men."
-
E.
Jesse Macht
Jesse Macht is an American singer-songwriter and musician known for his melodic pop-rock style and work as a solo artist and band member.
- 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_69d6ab287ba48190a5178779fd19b9b7 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8a69a099c8190a674db64c50eca5a |
completed | April 10, 2026, 7:28 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f281745ca88190968e1f674d0e483c |
completed | April 29, 2026, 10:08 p.m. |
| NEDg | Description generation | batch_69f28a8e64ac8190ba7637fd00e024bd |
completed | April 29, 2026, 10:47 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f28d4e341c8190abc8febc3b26a617 |
completed | April 29, 2026, 10:59 p.m. |
Created at: April 8, 2026, 9:43 p.m.