Triple
T18504311
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shoop |
E452160
|
entity |
| Predicate | writer |
P1360
|
FINISHED |
| Object |
Mark Sparks
Mark Sparks is a writer known for his work on the song "Shoop."
|
E1327859
|
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: Mark Sparks | Statement: [Shoop, writer, Mark Sparks]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mark Sparks Context triple: [Shoop, writer, Mark Sparks]
-
A.
Jeremy Sparks
Jeremy Sparks is an Australian figure best known as the husband of acclaimed actress and producer Claudia Karvan.
-
B.
Randy Sparks
Randy Sparks is an American musician, songwriter, and founder of the folk group The New Christy Minstrels, influential in the 1960s folk revival.
-
C.
Cole Palen
Cole Palen was an American aviation enthusiast and collector best known for creating and operating the Old Rhinebeck Aerodrome, a living museum of vintage aircraft and early aviation history.
-
D.
Sean Akins
Sean Akins is a television producer and creative director best known for helping develop and shape Cartoon Network’s influential Toonami programming block.
-
E.
Len Elmore
Len Elmore is a former American professional basketball player, college basketball star at the University of Maryland, and longtime television sports analyst and legal analyst.
- 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: Mark Sparks Triple: [Shoop, writer, Mark Sparks]
Generated description
Mark Sparks is a writer known for his work on the song "Shoop."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Mark Sparks Target entity description: Mark Sparks is a writer known for his work on the song "Shoop."
-
A.
Jeremy Sparks
Jeremy Sparks is an Australian figure best known as the husband of acclaimed actress and producer Claudia Karvan.
-
B.
Randy Sparks
Randy Sparks is an American musician, songwriter, and founder of the folk group The New Christy Minstrels, influential in the 1960s folk revival.
-
C.
Cole Palen
Cole Palen was an American aviation enthusiast and collector best known for creating and operating the Old Rhinebeck Aerodrome, a living museum of vintage aircraft and early aviation history.
-
D.
Sean Akins
Sean Akins is a television producer and creative director best known for helping develop and shape Cartoon Network’s influential Toonami programming block.
-
E.
Len Elmore
Len Elmore is a former American professional basketball player, college basketball star at the University of Maryland, and longtime television sports analyst and legal analyst.
- 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_69d8d386df84819092355ebb260d848e |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e53341063c81908361b0eb78794145 |
completed | April 19, 2026, 7:55 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0471456b348190a6bf62f1614f3d07 |
completed | May 13, 2026, 12:40 p.m. |
| NEDg | Description generation | batch_6a0472fee3a88190aa0cb5a8ff0af66a |
completed | May 13, 2026, 12:47 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0473fa3c5c8190aad12a5d952a796a |
completed | May 13, 2026, 12:52 p.m. |
Created at: April 10, 2026, 11:36 a.m.