Triple
T15080631
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Steve King |
E380129
|
entity |
| Predicate | precededBy |
P97
|
FINISHED |
| Object |
Greg Ganske
Greg Ganske is an American plastic surgeon and Republican politician who represented Iowa in the U.S. House of Representatives from 1995 to 2003.
|
E1239041
|
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: Greg Ganske | Statement: [Steve King, precededBy, Greg Ganske]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Greg Ganske Context triple: [Steve King, precededBy, Greg Ganske]
-
A.
Greg Latta
Greg Latta was an American professional football tight end who played in the World Football League and the NFL, most notably for the Chicago Bears.
-
B.
Jim Schoenecker
Jim Schoenecker is a musician best known for his past role in the experimental indie rock band Collections of Colonies of Bees.
-
C.
Jim Schoenecker
Jim Schoenecker is a contributor to the Unmap project, likely involved in its development or creative work.
-
D.
Brian Bockrath
Brian Bockrath is a television producer best known for his executive production work on the post-apocalyptic horror drama series The Walking Dead: Dead City.
-
E.
Greg Wuliger
Greg Wuliger is Chris Rock’s loyal, nerdy best friend in the sitcom "Everybody Hates Chris," known for his quirky personality and unwavering support.
- 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: Greg Ganske Triple: [Steve King, precededBy, Greg Ganske]
Generated description
Greg Ganske is an American plastic surgeon and Republican politician who represented Iowa in the U.S. House of Representatives from 1995 to 2003.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Greg Ganske Target entity description: Greg Ganske is an American plastic surgeon and Republican politician who represented Iowa in the U.S. House of Representatives from 1995 to 2003.
-
A.
Greg Latta
Greg Latta was an American professional football tight end who played in the World Football League and the NFL, most notably for the Chicago Bears.
-
B.
Jim Schoenecker
Jim Schoenecker is a contributor to the Unmap project, likely involved in its development or creative work.
-
C.
Jim Schoenecker
Jim Schoenecker is a musician best known for his past role in the experimental indie rock band Collections of Colonies of Bees.
-
D.
Brian Bockrath
Brian Bockrath is a television producer best known for his executive production work on the post-apocalyptic horror drama series The Walking Dead: Dead City.
-
E.
Greg Wuliger
Greg Wuliger is Chris Rock’s loyal, nerdy best friend in the sitcom "Everybody Hates Chris," known for his quirky personality and unwavering support.
- 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_69d85cd7683881908d405c1b5d7b4f7f |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69dff80008c88190840f94222f867478 |
completed | April 15, 2026, 8:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00c28d1e1c81909e869f01659ec233 |
completed | May 10, 2026, 5:38 p.m. |
| NEDg | Description generation | batch_6a00c457a1608190bd57155e91e55e9c |
completed | May 10, 2026, 5:45 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a00c5230fd481908cbc37e332b72380 |
completed | May 10, 2026, 5:49 p.m. |
Created at: April 10, 2026, 3:03 a.m.