Triple
T18372952
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | WKRP in Cincinnati |
E446231
|
entity |
| Predicate | hasCastMember |
P2308
|
FINISHED |
| Object |
Gary Sandy
Gary Sandy is an American actor best known for playing program director Andy Travis on the television sitcom "WKRP in Cincinnati."
|
E1321201
|
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: Gary Sandy | Statement: [WKRP in Cincinnati, hasCastMember, Gary Sandy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gary Sandy Context triple: [WKRP in Cincinnati, hasCastMember, Gary Sandy]
-
A.
Ron Todd
Ron Todd is an American politician who served as the Kansas Insurance Commissioner before Kathleen Sebelius.
-
B.
Ron Todd
Ron Todd was a prominent British trade union leader who served as a key figure in the labor movement during the late 20th century.
-
C.
Robert Wuhl
Robert Wuhl is an American actor, comedian, and writer best known for his roles in films like "Bull Durham" and "Batman" and for creating and starring in the HBO series "Arliss."
-
D.
Gordon Pinsent
Gordon Pinsent was a celebrated Canadian actor, writer, and director known for his prolific film, television, and stage career spanning several decades.
-
E.
Lee Stander
Lee Stander is known primarily as the spouse of American character actor Lionel Stander.
- 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: Gary Sandy Triple: [WKRP in Cincinnati, hasCastMember, Gary Sandy]
Generated description
Gary Sandy is an American actor best known for playing program director Andy Travis on the television sitcom "WKRP in Cincinnati."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Gary Sandy Target entity description: Gary Sandy is an American actor best known for playing program director Andy Travis on the television sitcom "WKRP in Cincinnati."
-
A.
Ron Todd
Ron Todd is an American politician who served as the Kansas Insurance Commissioner before Kathleen Sebelius.
-
B.
Ron Todd
Ron Todd was a prominent British trade union leader who served as a key figure in the labor movement during the late 20th century.
-
C.
Robert Wuhl
Robert Wuhl is an American actor, comedian, and writer best known for his roles in films like "Bull Durham" and "Batman" and for creating and starring in the HBO series "Arliss."
-
D.
Gordon Pinsent
Gordon Pinsent was a celebrated Canadian actor, writer, and director known for his prolific film, television, and stage career spanning several decades.
-
E.
Lee Stander
Lee Stander is known primarily as the spouse of American character actor Lionel Stander.
- 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_69d8b9f370b88190b1e5081c2c238e7f |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e517561edc8190b5d2834707ab662b |
completed | April 19, 2026, 5:56 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a03d77aa5788190bd1db34041de4966 |
completed | May 13, 2026, 1:44 a.m. |
| NEDg | Description generation | batch_6a03d83fe9a08190b18b9f61ee606372 |
completed | May 13, 2026, 1:47 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a03d915215c819090023094f1fc47f1 |
completed | May 13, 2026, 1:51 a.m. |
Created at: April 10, 2026, 10:45 a.m.