Triple
T22383881
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Diane Middlebrook |
E553342
|
entity |
| Predicate | notableSubjectOfWork |
P4941
|
FINISHED |
| Object |
Billy Tipton
Billy Tipton was an American jazz musician and bandleader who lived as a man for decades, with his assigned female sex only widely revealed after his death.
|
E1534809
|
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: Billy Tipton | Statement: [Diane Middlebrook, notableSubjectOfWork, Billy Tipton]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Billy Tipton Context triple: [Diane Middlebrook, notableSubjectOfWork, Billy Tipton]
-
A.
Merle Robbins
Merle Robbins was an American barber and game inventor best known for creating the popular card game Uno.
-
B.
Dody Teachman
Dody Teachman is an American figure skating coach best known for working with former U.S. champion Tonya Harding.
-
C.
Sam Englebardt
Sam Englebardt is a film producer and media investor known for backing genre films and emerging entertainment technologies.
-
D.
Edie Mani
Edie Mani is known as the wife of American actor Robert Carradine.
-
E.
Michael Learned
Michael Learned is an American actress best known for her Emmy-winning role as Olivia Walton on the television series "The Waltons."
- 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: Billy Tipton Triple: [Diane Middlebrook, notableSubjectOfWork, Billy Tipton]
Generated description
Billy Tipton was an American jazz musician and bandleader who lived as a man for decades, with his assigned female sex only widely revealed after his death.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Billy Tipton Target entity description: Billy Tipton was an American jazz musician and bandleader who lived as a man for decades, with his assigned female sex only widely revealed after his death.
-
A.
Merle Robbins
Merle Robbins was an American barber and game inventor best known for creating the popular card game Uno.
-
B.
Dody Teachman
Dody Teachman is an American figure skating coach best known for working with former U.S. champion Tonya Harding.
-
C.
Sam Englebardt
Sam Englebardt is a film producer and media investor known for backing genre films and emerging entertainment technologies.
-
D.
Edie Mani
Edie Mani is known as the wife of American actor Robert Carradine.
-
E.
Michael Learned
Michael Learned is an American actress best known for her Emmy-winning role as Olivia Walton on the television series "The Waltons."
- 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_69e11e4cf87c8190a1ff474daec326b7 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f1582d8e548190a7330de49d519675 |
completed | April 29, 2026, 1 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0ae9bc28fc81908967105a7a34903e |
completed | May 18, 2026, 10:28 a.m. |
| NEDg | Description generation | batch_6a0aedd061408190a25b6b1773e6610a |
completed | May 18, 2026, 10:45 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0aee8497b881909019717c6b9b4888 |
completed | May 18, 2026, 10:48 a.m. |
Created at: April 16, 2026, 8:45 p.m.