Triple
T1132539
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Davidson College |
E23063
|
entity |
| Predicate | president |
P8
|
FINISHED |
| Object |
Doug Hicks
Doug Hicks is an American academic and administrator who serves as the president of Davidson College in North Carolina.
|
E208204
|
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: Doug Hicks | Statement: [Davidson College, president, Doug Hicks]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Doug Hicks Context triple: [Davidson College, president, Doug Hicks]
-
A.
Kevin Hageman
Kevin Hageman is an American screenwriter and producer known for his work on animated and family films and television series, including contributions to The Lego Movie franchise.
-
B.
Jim Hines
Jim Hines was an American sprinter and Olympic gold medalist best known for being the first man to officially break the 10-second barrier in the 100-meter dash.
-
C.
Sam Wheeler
Sam Wheeler is the father of Ted Wheeler, the mayor of Portland, Oregon.
-
D.
Jim Kimsey
Jim Kimsey was an American businessman and philanthropist best known as a co-founder and the first CEO of the pioneering internet company AOL.
-
E.
Matthew Kirk
Matthew Kirk is a notable individual who shares the surname Kirk, recognized for achievements significant enough to be distinguished among others with the same name.
- 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: Doug Hicks Triple: [Davidson College, president, Doug Hicks]
Generated description
Doug Hicks is an American academic and administrator who serves as the president of Davidson College in North Carolina.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Doug Hicks Target entity description: Doug Hicks is an American academic and administrator who serves as the president of Davidson College in North Carolina.
-
A.
Kevin Hageman
Kevin Hageman is an American screenwriter and producer known for his work on animated and family films and television series, including contributions to The Lego Movie franchise.
-
B.
Jim Hines
Jim Hines was an American sprinter and Olympic gold medalist best known for being the first man to officially break the 10-second barrier in the 100-meter dash.
-
C.
Sam Wheeler
Sam Wheeler is the father of Ted Wheeler, the mayor of Portland, Oregon.
-
D.
Jim Kimsey
Jim Kimsey was an American businessman and philanthropist best known as a co-founder and the first CEO of the pioneering internet company AOL.
-
E.
Matthew Kirk
Matthew Kirk is a notable individual who shares the surname Kirk, recognized for achievements significant enough to be distinguished among others with the same name.
- 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_69a493ec75988190b63a11bafaec29b4 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4bbfcdf848190a2917d796ca84b74 |
completed | March 1, 2026, 10:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69add1a06d7c8190b6c38ff6d18a4542 |
completed | March 8, 2026, 7:44 p.m. |
| NEDg | Description generation | batch_69add34958448190a7d0fcbbf80cb484 |
completed | March 8, 2026, 7:51 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69add3ba5a688190a2040617b7e23083 |
completed | March 8, 2026, 7:53 p.m. |
Created at: March 1, 2026, 7:44 p.m.