Triple
T19186939
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | serum run to Nome |
E469724
|
entity |
| Predicate | significantPerson |
P643
|
FINISHED |
| Object |
Johnny Folger
Johnny Folger was one of the mushers who participated in the 1925 serum run to Nome, the historic dog-sled relay that delivered diphtheria antitoxin across Alaska.
|
E1362997
|
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: Johnny Folger | Statement: [serum run to Nome, significantPerson, Johnny Folger]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Johnny Folger Context triple: [serum run to Nome, significantPerson, Johnny Folger]
-
A.
Ernie Keebler
Ernie Keebler is the cheerful, cartoon elf mascot of the Keebler cookie brand, known for baking treats in a magical tree.
-
B.
Ian Fried
Ian Fried is a screenwriter best known for penning the supernatural thriller film "Spectral."
-
C.
Neil Hamburger
Neil Hamburger is the alter ego of American comedian Gregg Turkington, known for his deliberately awkward, anti-comedy stand-up persona and offbeat comedy albums.
-
D.
Fred Karger
Fred Karger was an American musician and vocal coach best known for his work at major Hollywood studios and his long, on-and-off marriage to actress Jane Wyman.
-
E.
David Sprecher
David Sprecher is an author known for his work related to streets and urban environments.
- 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: Johnny Folger Triple: [serum run to Nome, significantPerson, Johnny Folger]
Generated description
Johnny Folger was one of the mushers who participated in the 1925 serum run to Nome, the historic dog-sled relay that delivered diphtheria antitoxin across Alaska.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Johnny Folger Target entity description: Johnny Folger was one of the mushers who participated in the 1925 serum run to Nome, the historic dog-sled relay that delivered diphtheria antitoxin across Alaska.
-
A.
Ernie Keebler
Ernie Keebler is the cheerful, cartoon elf mascot of the Keebler cookie brand, known for baking treats in a magical tree.
-
B.
Ian Fried
Ian Fried is a screenwriter best known for penning the supernatural thriller film "Spectral."
-
C.
Neil Hamburger
Neil Hamburger is the alter ego of American comedian Gregg Turkington, known for his deliberately awkward, anti-comedy stand-up persona and offbeat comedy albums.
-
D.
Fred Karger
Fred Karger was an American musician and vocal coach best known for his work at major Hollywood studios and his long, on-and-off marriage to actress Jane Wyman.
-
E.
David Sprecher
David Sprecher is an author known for his work related to streets and urban environments.
- 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_69d8dd0ad9088190a173b32657ae2e7a |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5f620f1f08190a0daaf0d1483d724 |
completed | April 20, 2026, 9:47 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a06f8ba0a508190af6adb8ff3b8969e |
completed | May 15, 2026, 10:43 a.m. |
| NEDg | Description generation | batch_6a06f987d3e88190ade6412afd3e1426 |
completed | May 15, 2026, 10:46 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a06fa6c6e5481909beb3a33517264f3 |
completed | May 15, 2026, 10:50 a.m. |
Created at: April 10, 2026, 12:07 p.m.